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

    Neuronpedia

    INDEX
    Explanations

    terms related to interpersonal relationships and friendly behaviors

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

    friendly descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    /**
    -0.41
     russa
    -0.40
     enjeux
    -0.36
     planea
    -0.36
     jesu
    -0.35
     részt
    -0.34
     monasterio
    -0.34
    basicConfig
    -0.33
     planejamento
    -0.32
    cessite
    -0.32
    POSITIVE LOGITS
     friendly
    1.44
     Friendly
    1.34
    friendly
    1.34
    Friendly
    1.33
     friendliness
    1.19
     freundlichen
    0.98
     freundlich
    0.98
     unfriendly
    0.93
     vriende
    0.93
     freund
    0.91
    Act Density 0.013%

    No Known Activations