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

    Neuronpedia

    INDEX
    Explanations

    words related to social dynamics and interactions, such as cooperation, empathy, and challenges

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to conflict or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pwr
    -0.76
     GOODMAN
    -0.76
    pload
    -0.65
    abouts
    -0.60
    ornia
    -0.57
    itures
    -0.56
     Originally
    -0.56
    ificantly
    -0.56
    glomer
    -0.55
    zzi
    -0.53
    POSITIVE LOGITS
     motives
    0.65
     gull
    0.61
     emotion
    0.61
    ĸļ
    0.59
    enance
    0.58
     sincerity
    0.57
     plight
    0.57
     cand
    0.56
     unworthy
    0.55
    telling
    0.52
    Act Density 1.532%

    No Known Activations