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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opinions or statements made by someone

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ingu
    -0.72
    chnology
    -0.67
    onest
    -0.65
    omach
    -0.62
    renheit
    -0.62
    ardless
    -0.62
    ģ«
    -0.62
    anuts
    -0.61
    ablish
    -0.61
    isphere
    -0.61
    POSITIVE LOGITS
     says
    1.05
     said
    1.04
     replied
    1.03
     tweeted
    0.97
    said
    0.95
     wrote
    0.95
     reads
    0.93
     exclaimed
    0.92
     remarked
    0.91
     commented
    0.89
    Act Density 0.080%

    No Known Activations