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

    Neuronpedia

    INDEX
    Explanations

    speculative statements or expressions of uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     namely
    -0.53
     namelijk
    -0.45
     Awesome
    -0.43
    !
    -0.43
     invece
    -0.43
     Various
    -0.43
    に応じて
    -0.43
     приходится
    -0.42
    !!!
    -0.41
     geraten
    -0.41
    POSITIVE LOGITS
    IsMutable
    0.81
     subconsciously
    0.81
    twimg
    0.79
     propOrder
    0.79
    GEBURTSDATUM
    0.79
     الرياضيه
    0.78
    kháu
    0.78
    StructEnd
    0.77
     BoxFit
    0.77
     AttributeSet
    0.75
    Act Density 0.436%

    No Known Activations