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

    Neuronpedia

    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    timestamps or time-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prominently
    -0.63
    emouth
    -0.54
     kneeling
    -0.54
     corresponding
    -0.53
     availability
    -0.52
     ado
    -0.51
     presiding
    -0.51
     Vol
    -0.51
     ardent
    -0.51
     attendance
    -0.50
    POSITIVE LOGITS
    1969
    0.75
     dx
    0.70
    schild
    0.69
    roxy
    0.67
    WARNING
    0.63
    1959
    0.63
    INFO
    0.62
    angler
    0.61
    ancial
    0.61
    1971
    0.61
    Act Density 0.086%

    No Known Activations