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

    Neuronpedia

    INDEX
    Explanations

    dates or time expressions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rav
    -0.85
    itivity
    -0.82
    tons
    -0.76
    faced
    -0.75
    rition
    -0.74
    role
    -0.73
    resy
    -0.71
    zed
    -0.69
    aqu
    -0.69
    TEXT
    -0.68
    POSITIVE LOGITS
     afar
    1.22
     inception
    1.11
     January
    0.98
     scratch
    0.97
     dusk
    0.97
     conception
    0.96
     whence
    0.95
     1861
    0.94
     1951
    0.94
     1953
    0.93
    Act Density 0.112%

    No Known Activations