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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and codes related to classification or categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SION
    -0.17
    CREEN
    -0.17
    ENCIL
    -0.15
    ipop
    -0.14
    MBOL
    -0.14
    ERSION
    -0.14
    aclass
    -0.14
    ledon
    -0.14
    Å¡t
    -0.14
    comed
    -0.14
    POSITIVE LOGITS
    a
    0.26
    er
    0.22
    i
    0.22
    s
    0.21
    y
    0.20
    aft
    0.18
    zelf
    0.18
    ur
    0.17
    eÄį
    0.17
    t
    0.16
    Act Density 0.139%

    No Known Activations