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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating expectations or anticipations about actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    essler
    -0.17
    reau
    -0.17
    /books
    -0.16
     PureComponent
    -0.15
    auge
    -0.15
    تز
    -0.14
    ureau
    -0.14
    iba
    -0.14
    mbH
    -0.14
    ellow
    -0.14
    POSITIVE LOGITS
    oe
    0.18
    orate
    0.17
    airy
    0.15
    antly
    0.15
    æŀĿ
    0.14
    _NONNULL
    0.14
    à¸Ļà¹Ĩ
    0.14
    .shift
    0.14
    ê³
    0.14
    CAF
    0.13
    Act Density 0.049%

    No Known Activations