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

    Neuronpedia

    INDEX
    Explanations

    phrases or words that are deemed unusual or out of the ordinary

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "unusual" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    claimer
    -0.75
    hung
    -0.69
    chen
    -0.69
    ruction
    -0.67
    onest
    -0.67
    rio
    -0.67
    ophers
    -0.66
    zeb
    -0.66
    heit
    -0.65
    gets
    -0.65
    POSITIVE LOGITS
     occurrences
    1.06
    ities
    1.00
     circumstances
    0.95
     occurrence
    0.88
     anomal
    0.85
    worldly
    0.84
     deviations
    0.80
    ishly
    0.79
     circumstance
    0.79
     unanim
    0.79
    Act Density 0.021%

    No Known Activations