Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    comparative phrases indicating an increase in intensity or frequency

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing "becoming more" or "more" followed by an adjective or adverb, indicating increasing intensity or prevalence of something.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti

    phrases that indicate an increase or decrease in quantity or complexity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.87
     Flavoring
    -0.82
    chens
    -0.82
    glers
    -0.77
     Borders
    -0.69
    iversary
    -0.69
     Estimates
    -0.68
    ake
    -0.67
    adelphia
    -0.67
    pta
    -0.66
    POSITIVE LOGITS
     comfortable
    1.01
     attractive
    0.95
     agitated
    0.94
     aggressive
    0.93
     uneasy
    0.90
     uncomfortable
    0.90
     strained
    0.89
    aggressive
    0.88
     accustomed
    0.88
     reliant
    0.88
    Act Density 0.126%

    No Known Activations