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

    Neuronpedia

    INDEX
    Explanations

    key verbs and modal verbs indicating causality or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enta
    -0.15
     Chambers
    -0.15
    woods
    -0.15
    efs
    -0.14
     *----------------------------------------------------------------
    -0.14
    .telegram
    -0.14
    flag
    -0.14
    èı²
    -0.14
     нада
    -0.14
    eam
    -0.14
    POSITIVE LOGITS
    orate
    0.17
    alsy
    0.15
    ercul
    0.14
    eroon
    0.14
    акÑģим
    0.14
    iability
    0.14
     Corpus
    0.14
    erves
    0.14
     province
    0.14
     scre
    0.14
    Act Density 0.000%

    No Known Activations