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

    Neuronpedia

    INDEX
    Explanations

    actions related to giving and reciprocity in relationships

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

    give me, give them, give everyone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vigencia
    -0.37
     distrito
    -0.36
     gobernador
    -0.34
     Economía
    -0.33
     declaración
    -0.31
     Seguridad
    -0.31
     Desenvolvimento
    -0.31
     çalışmalar
    -0.31
     emoción
    -0.31
     évidence
    -0.30
    POSITIVE LOGITS
     autorytatywna
    0.66
    :✨
    0.56
    outSlope
    0.56
     mAdapter
    0.54
     متعلقه
    0.53
    haviours
    0.53
     BoxFit
    0.53
     betweenstory
    0.53
    GTCX
    0.53
    fanfic
    0.52
    Act Density 0.070%

    No Known Activations