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

    Neuronpedia

    INDEX
    Explanations

    comparisons related to quantities or superlatives

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases emphasizing uniqueness or distinction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isters
    -0.69
    ister
    -0.67
    assion
    -0.65
     Hare
    -0.65
    uay
    -0.65
    now
    -0.64
    onics
    -0.64
     1922
    -0.63
    staking
    -0.62
    ffee
    -0.62
    POSITIVE LOGITS
    worldly
    1.47
     conceivable
    0.92
     entity
    0.86
     major
    0.84
     aspect
    0.82
     imaginable
    0.76
    where
    0.75
    inant
    0.75
     circumstance
    0.75
     mammal
    0.74
    Act Density 0.045%

    No Known Activations