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

    Neuronpedia

    INDEX
    Explanations

    various symbols and markers commonly used in written text

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols commonly used in formatting or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itably
    -0.80
    orically
    -0.78
    bably
    -0.74
    ifting
    -0.72
    orical
    -0.71
    sworth
    -0.70
    nuts
    -0.70
    isphere
    -0.70
    agh
    -0.69
    ania
    -0.69
    POSITIVE LOGITS
    »
    0.95
    Prev
    0.83
     »
    0.81
    Ô
    0.72
     «
    0.70
     Kafka
    0.68
    dayName
    0.67
    Sov
    0.67
    Ü
    0.67
     âĢº
    0.66
    Act Density 0.012%

    No Known Activations