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

    Neuronpedia

    INDEX
    Explanations

    mentions of an increase in quantity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    topics related to firearms and their societal implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ij士
    -0.78
    escription
    -0.67
     Abdel
    -0.65
    ĺħ
    -0.64
    CHAT
    -0.63
    RAW
    -0.63
    cknow
    -0.63
     Whip
    -0.62
    arton
    -0.60
     Lazarus
    -0.60
    POSITIVE LOGITS
     than
    1.78
    than
    1.51
     Than
    1.21
    efficient
    0.85
    erous
    0.76
    worldly
    0.73
    rab
    0.70
     equals
    0.69
    catentry
    0.68
    izable
    0.68
    Act Density 0.374%

    No Known Activations