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

    Neuronpedia

    INDEX
    Explanations

    words associated with actions and social responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    viar
    -0.16
    isting
    -0.16
    ÙĨدگÛĮ
    -0.14
     dep
    -0.14
    udoku
    -0.14
     Pret
    -0.14
     Fell
    -0.14
    rello
    -0.13
    ivas
    -0.13
    itals
    -0.13
    POSITIVE LOGITS
    ée
    0.47
    és
    0.40
    ées
    0.39
    é
    0.39
    né
    0.26
    auté
    0.21
    lé
    0.21
    owany
    0.21
    ables
    0.20
    ant
    0.20
    Act Density 0.027%

    No Known Activations