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

    Neuronpedia

    INDEX
    Explanations

    words related to coincidences or unexpected occurrences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    severe
    -0.78
    bern
    -0.72
    ĨĴ
    -0.71
    ħĭ
    -0.71
    heit
    -0.71
    aton
    -0.66
    emouth
    -0.65
    Services
    -0.65
    artney
    -0.64
    unker
    -0.62
    POSITIVE LOGITS
     coincidence
    0.98
     coinc
    0.97
    idental
    0.95
    identally
    0.90
     coincided
    0.71
     coincide
    0.70
    idences
    0.68
    istically
    0.67
     coincides
    0.66
     occurrences
    0.64
    Act Density 15.184%

    No Known Activations