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

    Neuronpedia

    INDEX
    Explanations

    negations and instances of absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.51
     i
    -0.49
     et
    -0.48
     lo
    -0.44
    僕も
    -0.43
     car
    -0.42
     n
    -0.42
     U
    -0.41
     ve
    -0.41
    lot
    -0.40
    POSITIVE LOGITS
    ########.
    0.98
     صوتيه
    0.90
    帖最后由
    0.85
     مرئيه
    0.82
    ViewFeatures
    0.79
    enumii
    0.78
     تضيفلها
    0.77
    Diweddarwch
    0.77
    ControllerAdvice
    0.77
     pleaſure
    0.77
    Act Density 0.640%

    No Known Activations