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

    Neuronpedia

    INDEX
    Explanations

    terms related to global issues or phenomena

    oai_token-act-pair · gpt-3.5-turbo

    references to global warming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    maid
    -0.97
    veyard
    -0.94
    HOU
    -0.83
    ippi
    -0.80
    rentice
    -0.80
    sbm
    -0.80
    DragonMagazine
    -0.78
    roma
    -0.76
    yard
    -0.76
    manship
    -0.76
    POSITIVE LOGITS
     warming
    1.26
    ized
    0.97
    isation
    0.97
    ization
    0.87
     illumination
    0.87
     domination
    0.87
     positioning
    0.86
    ised
    0.86
    warming
    0.81
    izing
    0.81
    Act Density 0.032%

    No Known Activations