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

    Neuronpedia

    INDEX
    Explanations

    season numbers in TV show contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of seasons and episodes of television shows

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SourceFile
    -0.75
    omsky
    -0.72
    abase
    -0.71
    ventus
    -0.70
    edom
    -0.68
    ilian
    -0.66
    antry
    -0.65
    mart
    -0.65
    lihood
    -0.65
    reprene
    -0.65
    POSITIVE LOGITS
     Premiere
    0.83
     finale
    0.78
     Episode
    0.77
     premiere
    0.73
     premie
    0.71
     opener
    0.69
    oline
    0.66
     filler
    0.65
    Ĥİ
    0.65
     onwards
    0.62
    Act Density 0.138%

    No Known Activations