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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing agreement or the importance of dialogue

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ſtate
    -0.54
     houſe
    -0.54
     myſelf
    -0.53
     uſed
    -0.52
     ſever
    -0.52
     ſta
    -0.50
     ſon
    -0.50
     Dekker
    -0.48
     تضيفلها
    -0.48
    /**
    -0.48
    POSITIVE LOGITS
    uxxxx
    1.00
    rungsseite
    0.85
     חיצוניים
    0.83
    ftagPool
    0.76
     wireType
    0.74
    Наводи
    0.73
     @"/
    0.73
    oneofs
    0.73
     ویکی‌آمباردا
    0.71
    AndEndTag
    0.70
    Act Density 0.364%

    No Known Activations