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

    Neuronpedia

    INDEX
    Explanations

    ordinal numbers related to seasons or years

    oai_token-act-pair · gpt-3.5-turbo

    references to seasons, particularly in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bara
    -0.81
    skirts
    -0.78
     Tuls
    -0.77
    gemony
    -0.72
    glomer
    -0.71
    haven
    -0.66
    hovah
    -0.66
    argon
    -0.66
    urat
    -0.66
    rish
    -0.65
    POSITIVE LOGITS
     foray
    1.03
     outing
    1.00
     comeback
    0.97
     birthday
    0.96
     consecutive
    0.89
     adversary
    0.78
     appearance
    0.74
     career
    0.73
     debut
    0.73
     mortal
    0.73
    Act Density 0.058%

    No Known Activations