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

    Neuronpedia

    INDEX
    Explanations

    the occurrence of verbs indicating the beginning of actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llib
    -0.16
    ulence
    -0.15
    oops
    -0.15
    abama
    -0.15
    /bin
    -0.14
    riet
    -0.14
    vit
    -0.14
    at
    -0.14
    hawk
    -0.14
    ought
    -0.13
    POSITIVE LOGITS
    nings
    0.21
    urat
    0.17
    ãĤº
    0.15
    icont
    0.15
    /end
    0.15
    _unregister
    0.14
    itez
    0.14
    ãĥ³ãĥĩ
    0.14
    quet
    0.14
    FTA
    0.14
    Act Density 0.055%

    No Known Activations