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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numerical symbols in complex expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ody
    -0.16
    edd
    -0.15
    incerely
    -0.14
    ãĥªãĤ¢
    -0.14
    loy
    -0.14
     Bless
    -0.14
    away
    -0.13
     táºŃp
    -0.13
    inky
    -0.13
    liv
    -0.13
    POSITIVE LOGITS
     see
    0.28
     cf
    0.28
     i
    0.27
     e
    0.23
    cf
    0.20
     whose
    0.19
     independently
    0.18
    see
    0.18
     leading
    0.18
    whose
    0.18
    Act Density 0.147%

    No Known Activations