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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "create" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    c
    -0.19
    st
    -0.16
    red
    -0.15
    copy
    -0.15
    car
    -0.15
    ra
    -0.15
     intrinsic
    -0.14
    ri
    -0.14
    ab
    -0.14
    redi
    -0.14
    POSITIVE LOGITS
    edis
    0.18
    _singleton
    0.17
    elda
    0.17
    ddy
    0.16
    edBy
    0.16
    dux
    0.16
    neck
    0.15
    ault
    0.15
    tha
    0.15
    enberg
    0.15
    Act Density 0.172%

    No Known Activations