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

    Neuronpedia

    INDEX
    Explanations

    guidance on body language and manners in social interactions

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

    interpersonal conduct

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .*")]
    -0.51
    pausal
    -0.49
    fillType
    -0.45
    IndentedString
    -0.44
    openConnection
    -0.41
    DialogInterface
    -0.41
     Walkover
    -0.41
    GEBURTS
    -0.41
    TagMode
    -0.40
    gnus
    -0.40
    POSITIVE LOGITS
     cortesía
    0.54
     Infór
    0.51
    aarrggbb
    0.44
     Händen
    0.44
     literario
    0.44
     capucha
    0.44
     oreilles
    0.43
     Numerade
    0.42
     nahilalakip
    0.40
    pegno
    0.40
    Act Density 0.268%

    No Known Activations