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

    Neuronpedia

    INDEX
    Explanations

    terms related to initiating or bringing about significant changes or movements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to initiating or introducing significant changes or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pmwiki
    -0.78
    bian
    -0.74
    profits
    -0.66
    raid
    -0.65
    fts
    -0.62
     Agency
    -0.62
    edly
    -0.61
     deductible
    -0.61
    ombies
    -0.61
    obbies
    -0.61
    POSITIVE LOGITS
     usher
    1.27
     ushered
    1.09
    ĸļ
    0.90
    inson
    0.78
    wcs
    0.77
    olon
    0.72
    eering
    0.70
    eers
    0.70
    hetamine
    0.66
    ues
    0.66
    Act Density 0.010%

    No Known Activations