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

    Neuronpedia

    INDEX
    Explanations

    negative statements or situations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    doms
    -0.58
    arts
    -0.57
     pursuits
    -0.57
     creations
    -0.56
    eps
    -0.54
    iaries
    -0.53
    ritch
    -0.53
     Supported
    -0.52
    tein
    -0.52
    atic
    -0.51
    POSITIVE LOGITS
     room
    0.97
     unanim
    0.94
    hin
    0.92
     ample
    0.90
    ibaba
    0.89
     enough
    0.89
     plenty
    0.86
    enough
    0.85
     alot
    0.79
    something
    0.77
    Act Density 0.093%

    No Known Activations