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

    Neuronpedia

    INDEX
    Explanations

    references to individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "person"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.75
    enthal
    -0.69
    unctions
    -0.69
    è¦
    -0.68
     Equal
    -0.68
     Lions
    -0.67
     Lans
    -0.65
    Growing
    -0.65
    使
    -0.65
    DL
    -0.64
    POSITIVE LOGITS
    hood
    1.09
    nel
    0.91
    wise
    0.77
     else
    0.74
    istics
    0.72
    uscript
    0.71
    acles
    0.71
    acle
    0.71
    aganda
    0.70
    else
    0.70
    Act Density 0.030%

    No Known Activations