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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their variations in usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aign
    -0.17
    azz
    -0.16
    isans
    -0.15
    isas
    -0.14
    aze
    -0.14
    isque
    -0.14
    arsers
    -0.14
    olor
    -0.13
    orce
    -0.13
    gers
    -0.13
    POSITIVE LOGITS
    555
    0.18
    adow
    0.14
    lld
    0.14
    asso
    0.14
     Dough
    0.14
    htm
    0.13
    rox
    0.13
    -kit
    0.13
    anmar
    0.13
    ?family
    0.13
    Act Density 0.081%

    No Known Activations