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

    Neuronpedia

    INDEX
    Explanations

    boolean values related to conditional checks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inerary
    -0.62
     null
    -0.58
    quine
    -0.55
    lioma
    -0.55
     Koz
    -0.54
    quisar
    -0.54
    PARATOR
    -0.53
    ubei
    -0.53
     Sacrament
    -0.52
     Meal
    -0.52
    POSITIVE LOGITS
     False
    2.31
     True
    2.29
    False
    2.25
    True
    2.17
    FALSE
    1.27
     FALSE
    1.24
     TRUE
    1.24
    TRUE
    1.19
     Verdad
    0.93
    DoubleQuotes
    0.85
    Act Density 0.119%

    No Known Activations