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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal background, connections, and affiliations

    oai_token-act-pair · gpt-3.5-turbo

    statements related to personal opinions and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãģĻ
    -0.63
    iru
    -0.63
     Limit
    -0.60
    versible
    -0.59
    Temperature
    -0.59
    livion
    -0.59
     unlock
    -0.59
    emo
    -0.59
    agnetic
    -0.58
     NEXT
    -0.58
    POSITIVE LOGITS
     doubtless
    0.93
     incidentally
    0.86
     attest
    0.78
     likewise
    0.77
     certainly
    0.76
    sylv
    0.75
     vou
    0.75
     alumni
    0.74
     anecd
    0.74
     acquaintance
    0.72
    Act Density 1.146%

    No Known Activations