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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiment and partnership

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

    user posts text after start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    脚注の使い方
    -0.68
    #+#
    -0.63
     AssemblyCulture
    -0.54
    UrlResolution
    -0.52
     Италијани
    -0.50
    ValueStyle
    -0.47
    IntoConstraints
    -0.45
    帖最后由
    -0.44
     aDecoder
    -0.43
     <>",
    -0.43
    POSITIVE LOGITS
     Chwiliwch
    0.50
     كومونز
    0.45
     <<<<<<<<<<<<<<
    0.42
    ftagPool
    0.37
    quam
    0.34
     flask
    0.34
     beginnetje
    0.34
     ISNI
    0.34
    LabelTagHelper
    0.34
     winner
    0.34
    Act Density 0.011%

    No Known Activations