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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "to" and related infinitive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isco
    -0.15
    orgot
    -0.15
    ÑģÑı
    -0.15
    uzzi
    -0.14
     FORMAT
    -0.14
    baÅŁ
    -0.14
    aya
    -0.14
    urre
    -0.14
     Ih
    -0.13
    rored
    -0.13
    POSITIVE LOGITS
     behold
    0.17
    echa
    0.15
    boot
    0.15
    ryan
    0.15
    oting
    0.14
     canh
    0.14
    EC
    0.14
    ναν
    0.14
    /from
    0.14
     Lager
    0.14
    Act Density 0.062%

    No Known Activations