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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ces
    -0.17
    arks
    -0.16
    s
    -0.15
     bla
    -0.14
    uki
    -0.13
     Teen
    -0.13
     sim
    -0.13
    335
    -0.13
    ynn
    -0.13
    werk
    -0.13
    POSITIVE LOGITS
    theless
    0.18
    umbnail
    0.16
    lah
    0.15
    Bracket
    0.14
    à¸Ļะ
    0.14
    ese
    0.14
    .tokens
    0.14
    VERR
    0.14
    .RunWith
    0.14
    ÏĦαι
    0.14
    Act Density 0.027%

    No Known Activations