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

    Neuronpedia

    INDEX
    Explanations

    keywords associated with programming functions and parameters

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    respon
    -0.46
     (
    -0.45
    imo
    -0.43
    **
    -0.43
     Mr
    -0.42
    ack
    -0.42
    ult
    -0.42
     H
    -0.42
    </em>
    -0.41
    string
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.93
     كومونز
    0.89
     resourceCulture
    0.88
    tagHelperRunner
    0.88
     raiſ
    0.87
     BoxDecoration
    0.86
    DockStyle
    0.84
     pleaſure
    0.84
     auffi
    0.84
    saraba
    0.83
    Act Density 0.118%

    No Known Activations