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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    349
    -0.15
     laut
    -0.15
    lus
    -0.14
    aris
    -0.14
    ild
    -0.14
    mey
    -0.14
     taxation
    -0.14
    261
    -0.14
    lá
    -0.14
     spectral
    -0.13
    POSITIVE LOGITS
    izik
    0.15
    adÃŃ
    0.15
    urat
    0.15
    ocz
    0.15
    ساÙĦ
    0.15
    league
    0.15
    EO
    0.14
    iot
    0.14
    EW
    0.13
    ownt
    0.13
    Act Density 0.000%

    No Known Activations