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

    Neuronpedia

    INDEX
    Explanations

    special characters or unusual diacritics in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ware
    -0.17
    asca
    -0.16
    arsi
    -0.16
    com
    -0.15
    ous
    -0.15
    о
    -0.15
    orch
    -0.15
    fy
    -0.15
    ooks
    -0.14
    aka
    -0.14
    POSITIVE LOGITS
    stakes
    0.15
    lobal
    0.15
    elian
    0.15
    cker
    0.14
    zzo
    0.14
    dig
    0.14
    fulness
    0.14
    quiv
    0.14
    llib
    0.14
    ĵ
    0.14
    Act Density 0.075%

    No Known Activations