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

    Neuronpedia

    INDEX
    Explanations

    statements that assert truthfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tagHelperRunner
    -0.73
    yntaxException
    -0.71
    ⓧ
    -0.71
     AppBundle
    -0.70
     Monfieur
    -0.68
     ſche
    -0.68
     myſelf
    -0.65
     незавершена
    -0.65
    المناصب
    -0.64
    DeleteBehavior
    -0.63
    POSITIVE LOGITS
     believers
    0.84
     False
    0.81
    False
    0.80
     believer
    0.75
    false
    0.72
     false
    0.69
     blue
    0.64
     north
    0.63
     colors
    0.63
     True
    0.62
    Act Density 0.086%

    No Known Activations