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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a distinct comparison or exception

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a contrast or exception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tumble
    -0.57
    tailed
    -0.52
     hunted
    -0.52
    ":[{"
    -0.52
     tyr
    -0.50
    "},"
    -0.48
     toast
    -0.48
     reproduce
    -0.48
    OTT
    -0.47
    prus
    -0.47
    POSITIVE LOGITS
    heid
    1.24
    icularly
    0.99
    ments
    0.86
     from
    0.83
    ively
    0.83
    ensive
    0.82
    ranging
    0.80
    ional
    0.78
    orial
    0.77
    selves
    0.77
    Act Density 0.030%

    No Known Activations