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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating support or backing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alloca
    -0.16
    acct
    -0.16
    -sidebar
    -0.14
    leich
    -0.14
    unker
    -0.14
    etty
    -0.13
    ToObject
    -0.13
    stown
    -0.13
    osph
    -0.13
    OrUpdate
    -0.13
    POSITIVE LOGITS
    924
    0.14
     bre
    0.14
     huz
    0.14
    IAL
    0.14
    244
    0.14
    452
    0.13
    peror
    0.13
    urat
    0.13
     Fischer
    0.13
     ****************************************************************************
    0.13
    Act Density 0.028%

    No Known Activations