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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation marks indicating lists or separations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urance
    -0.16
    ugi
    -0.15
    antis
    -0.15
    çĦ¡ãģĹ
    -0.15
    æ¡Ĥ
    -0.14
    vn
    -0.14
    ourt
    -0.14
    icit
    -0.13
    onomy
    -0.13
    hn
    -0.13
    POSITIVE LOGITS
    uesta
    0.14
    ustil
    0.14
    å¼ı
    0.14
    eve
    0.14
    amarin
    0.14
    ä¸ĺ
    0.14
     ëıĮ
    0.14
    ATCH
    0.14
    rine
    0.13
    jom
    0.13
    Act Density 0.003%

    No Known Activations