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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gh
    -0.14
    abei
    -0.14
    ola
    -0.13
    bourg
    -0.13
    rlen
    -0.13
    ropp
    -0.13
    din
    -0.13
    æĬŀ
    -0.13
    velt
    -0.12
    .which
    -0.12
    POSITIVE LOGITS
     etc
    0.26
    etc
    0.22
    iban
    0.20
    gone
    0.16
     dig
    0.15
    Ä©
    0.14
    akedown
    0.14
    undry
    0.14
    kas
    0.14
    .problem
    0.13
    Act Density 0.290%

    No Known Activations