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

    Neuronpedia

    INDEX
    Explanations

    phrases that denote permission or allowance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YNC
    -0.83
     StatelessWidget
    -0.80
    ValueStyle
    -0.76
     بيها
    -0.76
    numerusform
    -0.74
    »?
    -0.74
     démission
    -0.73
     fatica
    -0.73
    SessionFactory
    -0.73
     Arxivat
    -0.71
    POSITIVE LOGITS
     ALLOW
    1.57
    ALLOW
    1.54
     Allow
    1.46
     allow
    1.44
     allowed
    1.44
     allows
    1.41
     Allows
    1.37
    Allow
    1.31
    Allows
    1.31
     allowing
    1.30
    Act Density 0.087%

    No Known Activations