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

    Neuronpedia

    INDEX
    Explanations

    references to intelligence measurements and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uin
    -0.22
    ewan
    -0.16
    ials
    -0.15
    icast
    -0.15
    ราà¸Ĭ
    -0.15
    rippling
    -0.14
    icago
    -0.14
    ichael
    -0.14
    ORIZONTAL
    -0.14
    ODB
    -0.14
    POSITIVE LOGITS
    и
    0.19
    er
    0.18
    s
    0.18
    ubit
    0.17
    ़
    0.17
    sa
    0.17
    ot
    0.16
    ois
    0.16
    eer
    0.16
    sd
    0.16
    Act Density 0.071%

    No Known Activations