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

    Neuronpedia

    INDEX
    Explanations

    terms related to positivity and negativity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.93
    OGND
    -0.84
    #+#
    -0.82
    Демографія
    -0.80
     للمعارف
    -0.79
    PerformLayout
    -0.78
     viewDidLoad
    -0.78
     صوتيه
    -0.78
    tagHelperRunner
    -0.78
    mishes
    -0.76
    POSITIVE LOGITS
    Neg
    0.74
     nég
    0.67
     neg
    0.67
     Neg
    0.63
     afternoons
    0.58
    neg
    0.55
     negation
    0.54
     mornings
    0.54
     nega
    0.54
    konomi
    0.54
    Act Density 0.223%

    No Known Activations