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

    Neuronpedia

    INDEX
    Explanations

    assertions of truthfulness or validity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rhymes
    -0.61
     Manchuria
    -0.54
    yntaxException
    -0.54
    etera
    -0.53
     Denna
    -0.52
     Epistle
    -0.52
    AutoScaleMode
    -0.52
    Sides
    -0.51
     AppBundle
    -0.51
     Cabello
    -0.51
    POSITIVE LOGITS
     False
    0.77
     Tru
    0.77
     True
    0.76
    (!__
    0.75
    False
    0.74
     TRUE
    0.70
     believers
    0.70
    isTrue
    0.70
    TRUE
    0.68
    uyler
    0.67
    Act Density 0.101%

    No Known Activations