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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and words that indicate relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edBy
    -0.16
    ibly
    -0.15
    ollider
    -0.15
    太éĥİ
    -0.15
    anes
    -0.14
    IDEO
    -0.14
    .asp
    -0.14
    ctions
    -0.14
    ibility
    -0.14
    ollah
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.16
    eh
    0.15
     tslint
    0.15
    ees
    0.14
    Thunk
    0.14
     albeit
    0.14
    Fld
    0.14
    eec
    0.14
    opaque
    0.14
    iro
    0.14
    Act Density 0.295%

    No Known Activations