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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conclusions or endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sortable
    -0.16
    eil
    -0.15
    تد
    -0.15
    ernet
    -0.14
    .interpolate
    -0.13
     separat
    -0.13
    gni
    -0.13
    ῦ
    -0.13
    ساÙĨ
    -0.13
    .amazonaws
    -0.13
    POSITIVE LOGITS
    ister
    0.16
    .scalablytyped
    0.15
    erk
    0.15
    indre
    0.15
    .weixin
    0.15
    .Toolkit
    0.15
    ibt
    0.14
     Jared
    0.14
    aket
    0.14
    /end
    0.14
    Act Density 0.276%

    No Known Activations