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

    Neuronpedia

    INDEX
    Explanations

    discussions related to legal and ethical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PreferredItem
    -0.54
     كومونز
    -0.53
     utafitiHapana
    -0.50
     ModelExpression
    -0.48
    Искәрмәләр
    -0.46
    RTSC
    -0.44
    rawDesc
    -0.43
    ChildScrollView
    -0.43
    UrlResolution
    -0.43
    StatusOK
    -0.42
    POSITIVE LOGITS
     aversion
    0.53
     avoidance
    0.50
     prohibit
    0.50
     forbids
    0.49
     forbidding
    0.49
     Numerade
    0.48
    avoid
    0.46
     prohibiting
    0.46
     betweenstory
    0.46
     forbid
    0.46
    Act Density 1.334%

    No Known Activations