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

    Neuronpedia

    INDEX
    Explanations

    numerical data and relevant statistics in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ungle
    -0.15
    umont
    -0.15
    ries
    -0.14
    ëŀ
    -0.14
    iae
    -0.14
    zp
    -0.14
    лаÑģ
    -0.14
    uzzi
    -0.13
    picker
    -0.13
    nection
    -0.13
    POSITIVE LOGITS
     both
    0.25
    both
    0.22
     two
    0.22
    两个
    0.20
     Nos
    0.18
     respectively
    0.18
    :both
    0.17
    :
    0.17
    two
    0.17
    _both
    0.17
    Act Density 0.288%

    No Known Activations