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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "though."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igo
    -0.16
    coe
    -0.15
    nt
    -0.15
    ydı
    -0.14
    ube
    -0.14
    ç·ł
    -0.14
    gon
    -0.14
    ìĦ¸
    -0.14
    enor
    -0.14
    ãĤ¶ãĥ¼
    -0.14
    POSITIVE LOGITS
    odor
    0.17
    enth
    0.16
    illing
    0.16
    ród
    0.15
    fois
    0.15
    ãģĬãĤĬ
    0.15
    oldt
    0.14
    ackle
    0.14
    onth
    0.14
     Khi
    0.14
    Act Density 0.020%

    No Known Activations