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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and phrases that imply connection or addition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    noinspection
    -0.17
    anford
    -0.16
    OrCreate
    -0.15
    /Foundation
    -0.15
    oke
    -0.15
    ãģªãģĮãĤī
    -0.15
    lassian
    -0.14
    гал
    -0.14
    activex
    -0.14
    ÄĽÅ¾
    -0.13
    POSITIVE LOGITS
     etc
    0.18
     overall
    0.18
     even
    0.17
     downright
    0.16
    /or
    0.15
    etc
    0.15
    ÄĻk
    0.15
    even
    0.15
    /from
    0.14
    å¨ĺ
    0.14
    Act Density 0.185%

    No Known Activations