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

    Neuronpedia

    INDEX
    Explanations

    placeholders or special formatting characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.62
    bootstrapcdn
    -0.62
    "?>
    -0.61
    хьтан
    -0.60
     laude
    -0.60
     Frey
    -0.59
    ffilm
    -0.58
    openSession
    -0.57
    InvalidProtocol
    -0.55
    __))
    -0.55
    POSITIVE LOGITS
    ouille
    0.61
    escent
    0.60
    cello
    0.59
     InputDecoration
    0.57
     Chbosky
    0.55
    issauga
    0.55
    expandindo
    0.55
    MemoryWarning
    0.54
    wój
    0.54
     Vare
    0.54
    Act Density 0.042%

    No Known Activations