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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and phrases related to physical violence

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences involving individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canaver
    -0.88
    nl
    -0.74
    Jess
    -0.73
    fing
    -0.67
    minist
    -0.67
    Asset
    -0.65
     Nanto
    -0.65
    itaire
    -0.64
    poons
    -0.62
     è£ıè
    -0.62
    POSITIVE LOGITS
    're
    0.77
     cooper
    0.74
    Äĩ
    0.73
    pta
    0.71
     refuse
    0.69
     menstru
    0.68
     died
    0.67
     passed
    0.65
     grew
    0.65
     emerge
    0.65
    Act Density 0.290%

    No Known Activations