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
     exha
    -0.69
     reluct
    -0.66
    phal
    -0.65
    ocene
    -0.63
    anova
    -0.63
    olson
    -0.63
    ozo
    -0.62
    estine
    -0.61
    esan
    -0.61
     plurality
    -0.61
    POSITIVE LOGITS
    00
    1.18
    01
    0.95
    30
    0.83
    50
    0.81
    009
    0.81
    004
    0.79
    25
    0.79
    20
    0.78
    0100
    0.76
    005
    0.76
    Act Density 0.037%

    No Known Activations