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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and references to individual experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hast
    -0.17
    ิà¸ĸ
    -0.16
     accord
    -0.16
    toJson
    -0.15
    bbe
    -0.15
     sens
    -0.15
     sez
    -0.15
     Regarding
    -0.14
     Regards
    -0.14
    posit
    -0.14
    POSITIVE LOGITS
     barley
    0.23
    statt
    0.15
    èĭ
    0.15
    ittings
    0.14
    lef
    0.14
    ÄįÃŃ
    0.14
     Narrow
    0.14
    訴
    0.14
    æĹģ
    0.14
    è¡Ľ
    0.14
    Act Density 0.674%

    No Known Activations