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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to emphasis or assertion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     apo
    -0.57
    vamente
    -0.54
    المشاركات
    -0.53
     beider
    -0.53
     betreft
    -0.52
    oluene
    -0.52
     recientemente
    -0.50
     Apo
    -0.50
     Orrell
    -0.50
    سف
    -0.49
    POSITIVE LOGITS
     مشين
    0.87
    thats
    0.85
    Thats
    0.84
     Thats
    0.81
    ValueStyle
    0.79
    enumi
    0.78
     actionTypes
    0.77
     That
    0.74
    NOPQRST
    0.73
    AndEndTag
    0.71
    Act Density 0.112%

    No Known Activations