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

    Neuronpedia

    INDEX
    Explanations

    keywords related to code or file types

    oai_token-act-pair · gpt-3.5-turbo

    JSON structure and syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \\\\\\\\
    -0.78
    ishment
    -0.72
    bage
    -0.65
     itself
    -0.64
     stimulus
    -0.62
     qualification
    -0.62
     predictor
    -0.61
     emission
    -0.60
    ISON
    -0.59
     behold
    -0.59
    POSITIVE LOGITS
    everal
    0.89
    ettings
    0.88
    hare
    0.85
    ucker
    0.80
    eper
    0.75
    etc
    0.74
    yout
    0.74
    hip
    0.73
    peed
    0.72
    hell
    0.72
    Act Density 0.695%

    No Known Activations