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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their contexts in written instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    code delimiters and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.46
    <eos>
    -0.42
     caballos
    -0.33
     curieux
    -0.33
    Whatever
    -0.32
     bad
    -0.31
    ↵↵
    -0.31
    templateUrl
    -0.30
    strijd
    -0.30
     growing
    -0.29
    POSITIVE LOGITS
     CreateTagHelper
    0.66
    FormTagHelper
    0.65
    ParallelGroup
    0.65
    出版年
    0.61
    afficheront
    0.60
    tagext
    0.60
    SharedCtor
    0.58
     كومونز
    0.57
     Administrativna
    0.57
    jsii
    0.55
    Act Density 0.034%

    No Known Activations