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

    Neuronpedia

    INDEX
    Explanations

    requests for inappropriate or harmful content.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz
    New Auto-Interp
    Negative Logits
     загру
    0.43
     loads
    0.42
     overloaded
    0.42
     riches
    0.42
     impatient
    0.41
    Nodes
    0.41
     отлич
    0.40
    ！
    0.40
     overloading
    0.40
    流
    0.40
    POSITIVE LOGITS
     harmless
    0.84
     legitt
    0.79
     legitimate
    0.73
     legít
    0.73
     permissible
    0.71
     lawful
    0.71
    あくまで
    0.68
     lawfully
    0.67
     innocuous
    0.67
     respectful
    0.64
    Act Density 1.771%

    No Known Activations