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

    Neuronpedia

    INDEX
    Explanations

    words that indicate habitual or regular actions or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    llib
    -0.16
    ius
    -0.15
     Specialist
    -0.14
     nerv
    -0.14
     Cooling
    -0.14
     má»
    -0.14
    Ä°Y
    -0.14
     Wave
    -0.14
    emie
    -0.14
    asco
    -0.13
    POSITIVE LOGITS
    Docs
    0.15
    izedName
    0.14
    à¹Ģหล
    0.14
    Spinner
    0.14
     usual
    0.14
    enza
    0.14
    kits
    0.14
    yx
    0.13
     fu
    0.13
     Braz
    0.13
    Act Density 0.185%

    No Known Activations