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

    Neuronpedia

    INDEX
    Explanations

    abbreviations related to various types of vehicles

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with judicial and vehicular contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kills
    -0.72
     Wilde
    -0.68
     Writer
    -0.67
     Immunity
    -0.66
    UA
    -0.64
     Pell
    -0.64
     Elves
    -0.63
     Writers
    -0.62
     Investigator
    -0.62
    wolves
    -0.61
    POSITIVE LOGITS
    ruction
    1.31
    anced
    1.12
    yright
    1.00
    ition
    0.98
    tenance
    0.95
    acters
    0.95
    roying
    0.95
    alog
    0.95
    oldown
    0.94
    ipment
    0.92
    Act Density 0.175%

    No Known Activations