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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating belief or confidence in being able to accomplish something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    furt
    -0.90
     Cheong
    -0.75
    teen
    -0.68
    quartered
    -0.66
    pend
    -0.62
    Loading
    -0.62
    76561
    -0.61
     Falling
    -0.61
    spection
    -0.61
    checking
    -0.60
    POSITIVE LOGITS
     afford
    1.23
    't
    1.14
     safely
    1.05
     withstand
    0.99
     achieve
    0.97
     manage
    0.97
     tolerate
    0.95
     handle
    0.95
     improve
    0.94
     cope
    0.94
    Act Density 0.191%

    No Known Activations