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

    Neuronpedia

    INDEX
    Explanations

    boolean values, specifically instances where the value is set to false

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AssemblyTitle
    -0.60
    RectangleBorder
    -0.57
    bootstrapcdn
    -0.53
    KommentareTeilen
    -0.52
    Exhibit
    -0.50
     Tivoli
    -0.50
     TQ
    -0.50
    vistar
    -0.50
    Spire
    -0.49
    Viking
    -0.48
    POSITIVE LOGITS
     false
    1.52
     False
    1.42
    false
    1.32
    False
    1.30
     FALSE
    1.09
     falsa
    1.02
     falso
    0.95
    FALSE
    0.93
     falsos
    0.93
     fausse
    0.93
    Act Density 0.069%

    No Known Activations