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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "twice" or its variations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reg
    -0.17
    oa
    -0.15
    rell
    -0.15
    .uc
    -0.15
    hausen
    -0.15
    ον
    -0.14
    eg
    -0.14
    och
    -0.14
    note
    -0.14
    ожд
    -0.14
    POSITIVE LOGITS
    /th
    0.20
    -thirds
    0.19
     dozen
    0.17
    ër
    0.16
    krom
    0.16
    /single
    0.15
    ldkf
    0.15
    -week
    0.15
    abal
    0.15
    idlo
    0.15
    Act Density 0.011%

    No Known Activations