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

    Neuronpedia

    INDEX
    Explanations

    concepts related to accountability and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ames
    -0.55
    simpleType
    -0.54
    astify
    -0.53
     ***!
    -0.52
    الحياه
    -0.51
    CppMethod
    -0.51
     CommonModule
    -0.50
     FAP
    -0.49
    randomUUID
    -0.47
    ToProps
    -0.47
    POSITIVE LOGITS
     hold
    1.80
    Hold
    1.79
     Holding
    1.77
    Holding
    1.77
     Hold
    1.77
     holds
    1.75
     holding
    1.73
    hold
    1.70
    holding
    1.69
     Holds
    1.68
    Act Density 0.169%

    No Known Activations