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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating substantial breaks or separations in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    addy
    -0.17
    eten
    -0.16
    eto
    -0.15
    avo
    -0.15
    áz
    -0.14
    楽
    -0.14
    erez
    -0.14
    æĬ
    -0.14
    vinces
    -0.14
    enth
    -0.14
    POSITIVE LOGITS
    onaut
    0.15
    iage
    0.15
    ye
    0.15
    oret
    0.14
    è¡Ĺéģĵ
    0.14
    gua
    0.13
    154
    0.13
    [mid
    0.13
     however
    0.13
    bat
    0.13
    Act Density 0.165%

    No Known Activations