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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuations indicating emphatic or significant elements in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uchos
    -0.15
     è¡
    -0.15
    égor
    -0.15
    emoc
    -0.15
    lico
    -0.15
    ledo
    -0.14
    UBLIC
    -0.14
    ãģıãĤĮ
    -0.14
    apel
    -0.14
    vecs
    -0.14
    POSITIVE LOGITS
    illy
    0.16
    eland
    0.15
     Shed
    0.15
    arend
    0.15
     sund
    0.14
    PHA
    0.14
    964
    0.14
    963
    0.14
     Loft
    0.14
    inois
    0.14
    Act Density 0.003%

    No Known Activations