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

    Neuronpedia

    INDEX
    Explanations

    instances of academic citations and reference formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unga
    -0.18
    dorf
    -0.16
    bet
    -0.15
    paren
    -0.15
    serve
    -0.14
    eton
    -0.14
    innen
    -0.14
    olik
    -0.14
    agua
    -0.14
    ismet
    -0.14
    POSITIVE LOGITS
    ichel
    0.16
    ÎĮ
    0.15
    лев
    0.14
    .intro
    0.14
    íĽĪ
    0.14
    .echo
    0.14
     reclaim
    0.14
     kus
    0.14
     ÙħÙĪب
    0.14
    CTL
    0.13
    Act Density 0.019%

    No Known Activations