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

    Neuronpedia

    INDEX
    Explanations

    references to celebrations or special occasions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "celebrate" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iban
    -0.79
    æ©Ł
    -0.76
    abases
    -0.73
    ridge
    -0.71
    olit
    -0.70
    voc
    -0.69
    por
    -0.69
    uci
    -0.68
    bit
    -0.67
    say
    -0.67
    POSITIVE LOGITS
     holidays
    1.05
     celebrating
    0.95
     celebrations
    0.93
     milestones
    0.91
     birthday
    0.89
     successes
    0.83
     Celebr
    0.83
     Thanksgiving
    0.82
     Celebration
    0.81
     anniversary
    0.80
    Act Density 0.058%

    No Known Activations