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

    Neuronpedia

    INDEX
    Explanations

    phrases that express duality or contrasting qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.86
    Hauptartikel
    -0.64
     مرئيه
    -0.61
     CURIAM
    -0.60
     doInBackground
    -0.60
    __":
    -0.57
     Choco
    -0.56
    ;->
    -0.56
    ganj
    -0.55
     Tub
    -0.54
    POSITIVE LOGITS
     sometimes
    0.93
     бывает
    0.83
    Sometimes
    0.77
    sometimes
    0.77
     manchmal
    0.76
     Sometimes
    0.76
     parfois
    0.72
     бывают
    0.71
     lho
    0.70
     fometimes
    0.69
    Act Density 0.246%

    No Known Activations