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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the words "real life" or "real-world" examples

    oai_token-act-pair · gpt-3.5-turbo

    references to real-life situations and occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    indal
    -0.84
    wagon
    -0.75
    pid
    -0.74
    edin
    -0.72
    xit
    -0.70
    lite
    -0.70
    mun
    -0.68
    ighting
    -0.66
    kept
    -0.66
    nell
    -0.66
    POSITIVE LOGITS
     scenarios
    0.99
     situations
    0.95
     examples
    0.92
     equivalents
    0.81
     embodiment
    0.80
     scenario
    0.80
     counterparts
    0.79
     occurrences
    0.79
     example
    0.76
     counterpart
    0.76
    Act Density 0.098%

    No Known Activations