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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating sentence endings and pauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    awa
    -0.17
    ipar
    -0.16
    anni
    -0.15
    Į
    -0.15
    ombine
    -0.15
    COPE
    -0.14
    ÑĪин
    -0.14
    abr
    -0.14
    ombok
    -0.14
    راÙĨÙĩ
    -0.14
    POSITIVE LOGITS
    bew
    0.15
    FTA
    0.14
     Crown
    0.14
     soluble
    0.14
    /he
    0.13
    lew
    0.13
     Ùħر
    0.13
    /native
    0.13
     PARAM
    0.13
     Brun
    0.13
    Act Density 0.044%

    No Known Activations