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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or lack of information about identities

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "who" indicating uncertainty about identity or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    framework
    -0.80
    MER
    -0.70
    retion
    -0.69
    emin
    -0.68
    strip
    -0.67
    warning
    -0.64
     Globe
    -0.64
    emp
    -0.62
    esm
    -0.62
    urg
    -0.61
    POSITIVE LOGITS
     else
    1.08
    soever
    1.04
     owns
    0.94
     exactly
    0.93
     cares
    0.91
     cared
    0.87
    abouts
    0.86
     owes
    0.85
    dinand
    0.83
     participates
    0.82
    Act Density 0.042%

    No Known Activations