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

    Neuronpedia

    INDEX
    Explanations

    names and descriptions of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /+
    -0.69
    /-
    -0.68
    )."
    -0.67
    .):
    -0.66
    ]."
    -0.66
    )?
    -0.65
     stabilization
    -0.65
    ctory
    -0.65
    actionDate
    -0.63
    ):
    -0.63
    POSITIVE LOGITS
     discovered
    0.99
     dreamed
    0.97
     volunteered
    0.93
     underwent
    0.92
     discovers
    0.92
     traveled
    0.92
     recounted
    0.92
     wandered
    0.91
     visited
    0.91
     noticed
    0.91
    Act Density 0.250%

    No Known Activations