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

    Neuronpedia

    INDEX
    Explanations

    words related to intelligence or ingenuity

    oai_token-act-pair · gpt-3.5-turbo

    the word "clever" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imester
    -0.68
    thood
    -0.67
    avored
    -0.66
    asta
    -0.65
    emb
    -0.65
     witnessed
    -0.65
     Alone
    -0.62
    alone
    -0.61
    astered
    -0.61
    ategory
    -0.61
    POSITIVE LOGITS
    ly
    1.33
    nesses
    1.02
     enough
    0.92
    glers
    0.83
     tricks
    0.81
    NESS
    0.80
    ness
    0.79
    fully
    0.78
     twist
    0.77
    sonian
    0.77
    Act Density 0.030%

    No Known Activations