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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "okay" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingleton
    -0.17
    urma
    -0.15
    827
    -0.15
    ynamo
    -0.15
    meli
    -0.15
    lore
    -0.15
    æ¯Ľ
    -0.15
    HELL
    -0.14
    imuth
    -0.14
     Md
    -0.14
    POSITIVE LOGITS
    lahoma
    0.20
    etz
    0.19
    eh
    0.17
    oke
    0.15
    ive
    0.15
    ies
    0.15
    arian
    0.15
    tober
    0.15
    idge
    0.14
    nes
    0.14
    Act Density 0.032%

    No Known Activations