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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'striking' or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegistryLite
    -0.54
    WriteLiteral
    -0.50
    oa̍t
    -0.48
    :✨
    -0.45
     CÁ
    -0.44
    KommentareTeilen
    -0.43
    setLayoutManager
    -0.42
    Styleable
    -0.42
     tastes
    -0.41
     colegas
    -0.41
    POSITIVE LOGITS
     striking
    0.84
     descending
    0.75
     descent
    0.72
     strikes
    0.71
     descend
    0.70
     descended
    0.66
     Striking
    0.65
     hypothesis
    0.65
     descends
    0.65
     Strikes
    0.64
    Act Density 0.475%

    No Known Activations