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

    Neuronpedia

    INDEX
    Explanations

    elements related to tagging and categorization in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilen
    -0.19
    erc
    -0.15
    adir
    -0.15
    pek
    -0.14
     +:+
    -0.14
     ãĥĶ
    -0.14
    icago
    -0.14
    AndWait
    -0.14
    abay
    -0.14
    ést
    -0.14
    POSITIVE LOGITS
    PLE
    0.15
    ged
    0.14
    icha
    0.14
    >tag
    0.14
    sth
    0.14
    OrNull
    0.13
    "math
    0.13
    CCCC
    0.13
    ellite
    0.13
     fit
    0.13
    Act Density 0.011%

    No Known Activations