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

    Neuronpedia

    INDEX
    Explanations

    dates and times

    oai_token-act-pair · gpt-3.5-turbo

    references to time or duration in the context of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    faced
    -0.76
    hops
    -0.73
    itivity
    -0.73
    resy
    -0.69
    cn
    -0.68
    faces
    -0.68
    eas
    -0.67
    seek
    -0.65
    rav
    -0.65
    needed
    -0.64
    POSITIVE LOGITS
     afar
    1.14
     inception
    1.06
     whence
    1.06
     1901
    0.92
     conception
    0.92
     thence
    0.89
     1951
    0.88
     dusk
    0.88
     1861
    0.86
     1955
    0.86
    Act Density 0.134%

    No Known Activations