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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly periods and commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agnost
    -0.15
    nist
    -0.14
    oub
    -0.14
    hti
    -0.14
    amoto
    -0.13
    udge
    -0.13
    s
    -0.13
    udem
    -0.12
    in
    -0.12
    T
    -0.12
    POSITIVE LOGITS
    .flink
    0.14
     *}
    0.13
     “
    0.13
    HING
    0.13
    :maj
    0.12
    άνÏĦα
    0.12
    imbus
    0.12
    iteDatabase
    0.12
    'gc
    0.12
    ubbo
    0.12
    Act Density 0.286%

    No Known Activations