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

    Neuronpedia

    INDEX
    Explanations

    comparisons involving the term "other"

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing the uniqueness or dominance of a subject relative to others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isters
    -0.84
    ordes
    -0.78
    gets
    -0.73
    ãĥ¼ãĤ¯
    -0.72
    ernels
    -0.71
    undreds
    -0.69
    ometimes
    -0.69
    ften
    -0.68
    staking
    -0.67
    bows
    -0.67
    POSITIVE LOGITS
    worldly
    1.71
     conceivable
    1.19
     aspect
    1.17
    iator
    1.14
     circumstance
    1.07
     imaginable
    1.06
     avenue
    1.01
     kind
    1.00
     entity
    0.98
     option
    0.95
    Act Density 0.037%

    No Known Activations