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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of year followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years in historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EStreamFrame
    -0.94
     classified
    -0.72
    EStream
    -0.70
    Reviewer
    -0.70
     Whats
    -0.68
     webcam
    -0.67
    Downloadha
    -0.67
    hement
    -0.66
     Nanto
    -0.60
    edIn
    -0.60
    POSITIVE LOGITS
    87
    1.20
    84
    1.15
    91
    1.12
    82
    1.12
    92
    1.12
    81
    1.11
    83
    1.11
    71
    1.08
    73
    1.08
    85
    1.07
    Act Density 0.061%

    No Known Activations