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

    Neuronpedia

    INDEX
    Explanations

    words or expressions related to negative language and profanity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Xna
    -0.47
    Referències
    -0.47
     Mön
    -0.43
    DispatchToProps
    -0.38
     Namens
    -0.38
    Revenir
    -0.37
    atorics
    -0.36
     dosis
    -0.36
    ánchez
    -0.35
     מוכ
    -0.35
    POSITIVE LOGITS
     betweenstory
    0.81
     ProtoMessage
    0.79
     كومونز
    0.78
    AndEndTag
    0.75
    featureID
    0.69
    StoryboardSegue
    0.68
     HasFactory
    0.67
    FunctionFlags
    0.66
     للاسماء
    0.65
    }{*}{
    0.65
    Act Density 0.212%

    No Known Activations