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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members and authority figures in relation to decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     (
    -0.16
    ,
    -0.15
    ponents
    -0.15
    iddle
    -0.14
     Hed
    -0.14
    ảo
    -0.14
     Scar
    -0.14
    emer
    -0.14
    omat
    -0.14
    maker
    -0.14
    POSITIVE LOGITS
    readcr
    0.16
    ylie
    0.15
    ãĥĥãĥģ
    0.15
    سÙĪ
    0.14
    Dims
    0.14
    oyal
    0.14
    ouz
    0.14
     EXEMPLARY
    0.14
    aggable
    0.13
    ünd
    0.13
    Act Density 0.371%

    No Known Activations