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

    Neuronpedia

    INDEX
    Explanations

    dates or specific days mentioned in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days or significant events associated with particular days

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cephal
    -0.72
    hesive
    -0.72
    alach
    -0.71
    uctor
    -0.70
    agra
    -0.68
    igon
    -0.68
    pie
    -0.66
    unct
    -0.66
    umbn
    -0.65
    asc
    -0.65
    POSITIVE LOGITS
     occasion
    0.97
     occasions
    0.94
     eve
    0.90
     Feast
    0.75
     heels
    0.75
     Sabbath
    0.74
     basis
    0.74
     mornings
    0.73
    azo
    0.70
     doorstep
    0.69
    Act Density 0.074%

    No Known Activations