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

    Neuronpedia

    INDEX
    Explanations

    references to crime-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NewUrlParser
    -0.57
     GenerationType
    -0.49
     wireType
    -0.47
    GTCX
    -0.46
    sidemargin
    -0.45
    AutoScaleMode
    -0.45
    InputTagHelper
    -0.44
     يتيمه
    -0.42
    contentLoaded
    -0.42
    AutoresizingMask
    -0.41
    POSITIVE LOGITS
     security
    0.87
    Security
    0.80
     Security
    0.79
    治安
    0.79
    security
    0.76
     keamanan
    0.75
     امن
    0.74
     sécurité
    0.73
    violence
    0.73
     violence
    0.73
    Act Density 0.381%

    No Known Activations