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

    Neuronpedia

    INDEX
    Explanations

    mathematical operators and symbols typically used in formal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.53
     Ever
    -0.45
     im
    -0.45
     ever
    -0.44
    })();
    -0.42
    ever
    -0.41
     son
    -0.41
     t
    -0.41
     EVER
    -0.41
     Ben
    -0.40
    POSITIVE LOGITS
    rawDesc
    0.87
     industriels
    0.79
    AddTagHelper
    0.78
     Wikimedijinoj
    0.78
    Datuak
    0.76
    __(/*!
    0.75
    AndEndTag
    0.74
    tagext
    0.74
    Geplaatst
    0.73
     isolada
    0.73
    Act Density 1.272%

    No Known Activations