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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating potential for future actions or results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enne
    -0.15
    ове
    -0.15
    ãĥ³ãĥĩ
    -0.15
     stake
    -0.15
    vas
    -0.14
     neod
    -0.14
    usz
    -0.14
    ãĥ¥
    -0.14
    enant
    -0.14
    hen
    -0.14
    POSITIVE LOGITS
    coe
    0.16
    elian
    0.16
    obby
    0.15
    ToPoint
    0.15
     Ib
    0.15
    idian
    0.14
     cle
    0.14
    591
    0.14
    elight
    0.13
    chie
    0.13
    Act Density 0.003%

    No Known Activations