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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    afari
    -0.16
    Misc
    -0.15
    ủi
    -0.15
    azel
    -0.14
    rana
    -0.14
    neau
    -0.14
     #__
    -0.13
     Imported
    -0.13
    /apis
    -0.13
    Ĥæķ°
    -0.13
    POSITIVE LOGITS
    abstract
    0.28
    use
    0.27
     abstract
    0.27
    class
    0.25
     use
    0.25
     Abstract
    0.24
     class
    0.22
    Abstract
    0.22
     trait
    0.20
     spl
    0.20
    Act Density 0.004%

    No Known Activations