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

    Neuronpedia

    INDEX
    Explanations

    statements about potential outcomes or consequences associated with actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.60
     venuto
    -0.59
     OFDb
    -0.59
    الدراسه
    -0.59
     CURIAM
    -0.56
     createState
    -0.54
    UIControlState
    -0.54
     Warming
    -0.53
     Gifford
    -0.52
    Iceland
    -0.52
    POSITIVE LOGITS
     sometimes
    0.96
     potentially
    0.83
     akár
    0.81
    有时候
    0.78
     depending
    0.75
     бывает
    0.74
    Sometimes
    0.74
    sometimes
    0.74
     ibland
    0.73
     Sometimes
    0.73
    Act Density 0.332%

    No Known Activations