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

    Neuronpedia

    INDEX
    Explanations

    dates and temporal information

    oai_token-act-pair · gpt-3.5-turbo

    dates and durations related to events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orio
    -0.84
    Zone
    -0.78
    ctors
    -0.74
    aila
    -0.72
    pta
    -0.70
    osuke
    -0.68
    area
    -0.68
    erno
    -0.66
    FP
    -0.65
    pson
    -0.64
    POSITIVE LOGITS
     reverber
    0.78
     paralle
    0.68
     itself
    0.68
     culmin
    0.67
     declass
    0.65
     accordingly
    0.65
     corro
    0.64
     almost
    0.63
     constit
    0.63
     corrobor
    0.63
    Act Density 1.123%

    No Known Activations