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

    Neuronpedia

    INDEX
    Explanations

    words related to unexpected events or situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "unexpected."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nan
    -0.96
    ateurs
    -0.85
    ogun
    -0.85
    claimer
    -0.85
    xia
    -0.84
    builders
    -0.83
    rated
    -0.82
    tha
    -0.82
    etics
    -0.81
    tein
    -0.79
    POSITIVE LOGITS
     unexpected
    0.94
    aneously
    0.86
    LY
    0.83
     occurrences
    0.82
    cffffcc
    0.82
     twists
    0.77
     surprises
    0.76
     pregnancies
    0.76
     circumstances
    0.76
     revelations
    0.72
    Act Density 0.025%

    No Known Activations