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

    Neuronpedia

    INDEX
    Explanations

    proper names surrounded by quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    special characters, particularly quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alysed
    -0.84
     apex
    -0.75
    */(
    -0.74
    inary
    -0.70
    =>
    -0.70
    cms
    -0.69
    cffffcc
    -0.69
    actual
    -0.68
    pected
    -0.68
    exclusive
    -0.67
    POSITIVE LOGITS
     Andersen
    1.17
     Johnson
    1.15
     Christensen
    1.13
     Roberts
    1.13
     Ventura
    1.13
     Thompson
    1.09
     Greene
    1.09
     Hansen
    1.09
     Robinson
    1.08
     Caldwell
    1.08
    Act Density 0.044%

    No Known Activations