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

    Neuronpedia

    INDEX
    Explanations

    action verbs and phrases related to positive attitudes and behaviors

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    pora
    -0.83
    etheus
    -0.75
    successfully
    -0.74
    even
    -0.70
    rimination
    -0.67
    eatures
    -0.66
     likewise
    -0.65
    afort
    -0.65
    ornia
    -0.64
    amia
    -0.64
    POSITIVE LOGITS
    ifiable
    0.77
     coincidence
    0.74
     Facts
    0.72
     darn
    0.70
     plain
    0.69
     shrug
    0.68
     dudes
    0.66
    fuck
    0.65
     shrugged
    0.65
     curiosity
    0.65
    Act Density 0.282%

    No Known Activations