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

    Neuronpedia

    INDEX
    Explanations

    instances of the letter "s" or the possessive form "s'"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngr
    -0.18
    cles
    -0.17
    ampa
    -0.16
    lse
    -0.16
    olas
    -0.15
    imest
    -0.15
    izr
    -0.14
    inx
    -0.14
    ERRU
    -0.14
    isay
    -0.14
    POSITIVE LOGITS
    ãĥªãĤ¢
    0.16
    ere
    0.15
     Bench
    0.15
    ear
    0.15
     Bach
    0.15
    bern
    0.14
    ria
    0.14
    eler
    0.14
    iele
    0.14
    Ģ
    0.14
    Act Density 0.028%

    No Known Activations