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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of being "blind" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "blind" and its variations, often in contexts related to ignorance or oversight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xit
    -0.85
    cially
    -0.83
    afort
    -0.73
    idian
    -0.71
    andum
    -0.70
    bourg
    -0.69
     Heights
    -0.66
     Sunrise
    -0.65
    CE
    -0.63
     Occupations
    -0.63
    POSITIVE LOGITS
    fold
    1.47
    sided
    1.45
    sight
    1.31
    spot
    1.24
    ingly
    1.23
    side
    1.01
    eyed
    0.99
     alley
    0.95
    sighted
    0.95
     spots
    0.89
    Act Density 0.054%

    No Known Activations