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

    Neuronpedia

    INDEX
    Explanations

    specific times and locations, possibly from news reports

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pac
    -0.74
    FTWARE
    -0.72
    biased
    -0.71
    hops
    -0.71
    Lens
    -0.70
    ratulations
    -0.68
    ption
    -0.67
    VIDEO
    -0.67
    hop
    -0.66
    HTTP
    -0.66
    POSITIVE LOGITS
     least
    1.19
    onement
    1.07
     midday
    1.02
     midnight
    1.02
     halftime
    0.98
     dusk
    0.97
    abase
    0.97
    rium
    0.96
     noon
    0.95
    rial
    0.94
    Act Density 0.237%

    No Known Activations