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

    Neuronpedia

    INDEX
    Explanations

    instances of significant numbers or values indicated in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -1.04
    بوابة
    -0.80
    Portale
    -0.77
    LookAnd
    -0.72
    djangoproject
    -0.66
     الدولى
    -0.66
    <()>
    -0.62
     kaarangay
    -0.62
    المشاركات
    -0.61
    Étape
    -0.60
    POSITIVE LOGITS
    None
    0.70
     None
    0.70
     neither
    0.63
     none
    0.59
     NotImplemented
    0.59
     peines
    0.56
    none
    0.55
     not
    0.50
     nothing
    0.48
     Neither
    0.48
    Act Density 0.465%

    No Known Activations