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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permission or allowance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     StatelessWidget
    -0.79
    numerusform
    -0.79
     بيها
    -0.76
    ValueStyle
    -0.74
    tagext
    -0.74
    InitVars
    -0.74
     Ceinture
    -0.73
    YNC
    -0.73
    cobra
    -0.72
    SessionFactory
    -0.72
    POSITIVE LOGITS
    ALLOW
    1.74
     ALLOW
    1.74
     Allow
    1.68
     allow
    1.67
     allowed
    1.63
     allows
    1.59
     Allows
    1.56
    Allow
    1.53
     allowing
    1.50
    allow
    1.48
    Act Density 0.078%

    No Known Activations