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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brock
    -0.16
    .jet
    -0.15
     hers
    -0.15
    ilio
    -0.14
     Bryce
    -0.14
    imat
    -0.14
    pez
    -0.14
     Jaune
    -0.14
    xca
    -0.13
    æ·»
    -0.13
    POSITIVE LOGITS
     respectively
    0.17
    ész
    0.16
    iyon
    0.15
     Inc
    0.15
    anger
    0.15
    estr
    0.15
    -valu
    0.14
    ãĥķãĤ§
    0.14
    aded
    0.13
    avad
    0.13
    Act Density 0.064%

    No Known Activations