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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to educational institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to the character Darth Vader and related thematic elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mercial
    -0.75
    eared
    -0.70
    ournals
    -0.70
    PLA
    -0.67
    zees
    -0.65
    cise
    -0.65
    arettes
    -0.64
    ERC
    -0.64
    pper
    -0.64
     sidx
    -0.63
    POSITIVE LOGITS
    ritis
    1.28
     Vader
    0.90
    rell
    0.81
    rums
    0.81
    rian
    0.79
    rians
    0.77
    aja
    0.74
    arth
    0.73
    rum
    0.72
    awi
    0.71
    Act Density 0.007%

    No Known Activations