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

    Neuronpedia

    INDEX
    Explanations

    evaluative words and phrases related to criticism and analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Configure
    -0.38
    transform
    -0.35
    ecirc
    -0.32
    DISABLE
    -0.32
    irent
    -0.32
    общение
    -0.31
     دون
    -0.31
     transform
    -0.31
    sillo
    -0.31
     Miracle
    -0.31
    POSITIVE LOGITS
     ModelExpression
    0.73
    Worse
    0.66
     Worse
    0.65
     worse
    0.64
    worse
    0.56
    PropertyChanging
    0.52
    FormState
    0.52
    SharedDtor
    0.50
    UnitTesting
    0.49
    StructEnd
    0.48
    Act Density 0.482%

    No Known Activations