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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to social skills and their applications in relationships and influence

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

    social descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    庁
    -0.40
     cường
    -0.37
    lossians
    -0.36
     kwal
    -0.35
     Krieg
    -0.35
    尽く
    -0.33
     financeira
    -0.33
     eletr
    -0.33
     T
    -0.33
     Strecke
    -0.33
    POSITIVE LOGITS
    Social
    1.58
     social
    1.57
    social
    1.55
     SOCIAL
    1.49
     Social
    1.49
    SOCIAL
    1.41
     sociale
    1.41
     sociales
    1.38
     sociaux
    1.29
     sozialen
    1.23
    Act Density 0.046%

    No Known Activations