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

    Neuronpedia

    INDEX
    Explanations

    words related to personality traits and behaviors, specifically focusing on social interactions and physical characteristics

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of social and personality traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ´ãĥ³
    -0.76
    ioxide
    -0.75
    UNCH
    -0.75
    antha
    -0.74
    ERO
    -0.74
    ptions
    -0.74
    AMS
    -0.73
    ISA
    -0.72
    WIND
    -0.71
    ACA
    -0.70
    POSITIVE LOGITS
     minded
    1.21
     spirited
    0.92
    ness
    0.87
     enough
    0.86
     paced
    0.86
    minded
    0.78
    nered
    0.78
    ly
    0.77
     sounding
    0.76
    hearted
    0.76
    Act Density 0.297%

    No Known Activations