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

    Neuronpedia

    INDEX
    Explanations

    occurrences of utility-related terms in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tiener
    -0.15
    iol
    -0.15
    ãĤĨ
    -0.14
    inely
    -0.14
     Protection
    -0.14
    istrovstvÃŃ
    -0.14
    hong
    -0.14
    ÃŃrk
    -0.14
     Fet
    -0.14
     geme
    -0.14
    POSITIVE LOGITS
    itty
    0.15
     fanatic
    0.14
    à¥ĩà¤
    0.14
     nond
    0.14
     Turnbull
    0.14
    trial
    0.14
    ace
    0.14
     EG
    0.14
    weg
    0.13
    ãģĻãģİ
    0.13
    Act Density 0.003%

    No Known Activations