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

    Neuronpedia

    INDEX
    Explanations

    examples or instances

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce examples or illustrative cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rodham
    -0.78
     Mehran
    -0.68
    psey
    -0.61
     Guant
    -0.59
    "—
    -0.59
    \.
    -0.58
     ÂŃ
    -0.56
    Ö
    -0.55
    assador
    -0.55
    ],"
    -0.54
    POSITIVE LOGITS
    Example
    0.79
     drawback
    0.79
     Example
    0.75
     Examples
    0.73
    cknowled
    0.72
     downside
    0.70
    oret
    0.68
     disadvantages
    0.68
    Additionally
    0.67
     example
    0.66
    Act Density 0.728%

    No Known Activations