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

    Neuronpedia

    INDEX
    Explanations

    technological terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    repeated conjunctions and the use of the word "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fit
    -0.82
    Ĭ±
    -0.73
    Gamer
    -0.72
    tick
    -0.71
    habi
    -0.71
    fn
    -0.70
    Ĥİ
    -0.69
    gamer
    -0.68
    Ñı
    -0.67
    taking
    -0.67
    POSITIVE LOGITS
     assorted
    1.22
     possibly
    0.94
     finally
    0.92
     optionally
    0.83
    cellaneous
    0.76
     perhaps
    0.75
     etc
    0.74
     yes
    0.72
     occasional
    0.72
     desserts
    0.70
    Act Density 0.170%

    No Known Activations