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

    Neuronpedia

    INDEX
    Explanations

    printf and related syntax commonly used in programming

    oai_token-act-pair · gpt-3.5-turbo

    programming language keywords and print statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    avorite
    -0.79
    hots
    -0.73
    agonists
    -0.73
    icum
    -0.72
    wana
    -0.70
    hips
    -0.69
    hra
    -0.69
    arsity
    -0.68
    ality
    -0.68
    ospons
    -0.68
    POSITIVE LOGITS
     "\
    1.03
     "%
    1.02
     "$
    1.00
     "<
    0.96
     "(
    0.86
     "{
    0.84
    Line
    0.83
    ("
    0.82
     "[
    0.80
     "#
    0.79
    Act Density 0.039%

    No Known Activations