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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and designations in a document, indicating a focus on formatting or structural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Feinstein
    -0.17
    uga
    -0.16
    emes
    -0.15
    egas
    -0.15
    oding
    -0.14
    uggle
    -0.14
    456
    -0.14
     çĬ
    -0.14
    oral
    -0.14
     Amb
    -0.14
    POSITIVE LOGITS
     fraction
    0.20
    Fraction
    0.17
    licative
    0.16
     fractions
    0.15
    ãĤ¤ãĥ¤
    0.15
     Fraction
    0.15
     ç§
    0.15
    анÑģ
    0.15
    ivÄĽ
    0.14
    enville
    0.14
    Act Density 0.027%

    No Known Activations