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

    Neuronpedia

    INDEX
    Explanations

    punctuation and numerical separators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Developer
    -0.17
    á»ı
    -0.17
    afil
    -0.16
    iciel
    -0.15
    uchos
    -0.15
    eeper
    -0.15
    onne
    -0.14
    gm
    -0.14
    veloper
    -0.14
    .openg
    -0.14
    POSITIVE LOGITS
    antee
    0.19
    岸
    0.15
     Trot
    0.15
    á»Ļt
    0.15
    chie
    0.15
    unci
    0.15
    Boss
    0.14
    oha
    0.14
    urt
    0.14
    oreach
    0.14
    Act Density 0.064%

    No Known Activations