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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /lg
    -0.14
    ñana
    -0.14
    ëĥ
    -0.14
    unda
    -0.14
    ÐĿÐIJ
    -0.13
    anche
    -0.13
    okud
    -0.13
     सम
    -0.13
    ÅĻÃŃ
    -0.13
    olean
    -0.13
    POSITIVE LOGITS
    soever
    0.16
    dens
    0.15
    ships
    0.15
    inton
    0.15
    æ¢
    0.14
    sd
    0.14
    andon
    0.14
     æ¢
    0.14
    ron
    0.14
    fic
    0.14
    Act Density 0.047%

    No Known Activations