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

    Neuronpedia

    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     comprises
    -0.71
     resembles
    -0.69
     depended
    -0.68
     differs
    -0.68
     differed
    -0.66
     collided
    -0.66
     requires
    -0.65
     lacked
    -0.64
     encompasses
    -0.64
     accelerated
    -0.64
    POSITIVE LOGITS
     Walters
    0.83
     Hansen
    0.79
     McH
    0.79
    bart
    0.79
     Davies
    0.77
     Barker
    0.76
     Atkinson
    0.76
     Coffin
    0.75
     Andersen
    0.74
     Bauer
    0.73
    Act Density 0.368%

    No Known Activations