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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns and sequences

    oai_token-act-pair · gpt-3.5-turbo

    numerical identifiers or values within potentially legal or regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiName
    -0.85
    accompan
    -0.67
     asses
    -0.64
     [];
    -0.63
    .''
    -0.63
    javascript
    -0.62
    iencies
    -0.61
     '.
    -0.61
     [...]
    -0.60
    ''.
    -0.60
    POSITIVE LOGITS
    )"
    1.39
    ),"
    1.30
    )/
    1.28
    )
    1.22
    )",
    1.20
    )--
    1.20
    )—
    1.12
    ):
    1.11
    *)
    1.09
    )]
    1.07
    Act Density 0.157%

    No Known Activations