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

    Neuronpedia

    INDEX
    Explanations

    words related to extremity or intensity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "completely" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rers
    -0.72
    yip
    -0.72
    maid
    -0.72
    pires
    -0.69
    achu
    -0.69
    anners
    -0.69
    cffff
    -0.67
    iers
    -0.66
    anwhile
    -0.66
    ulton
    -0.66
    POSITIVE LOGITS
     unrelated
    0.80
     exempt
    0.75
     obliter
    0.73
     disregard
    0.72
     reliant
    0.72
     dependent
    0.70
    BuyableInstoreAndOnline
    0.69
     qualified
    0.69
    wash
    0.69
     annihil
    0.68
    Act Density 0.029%

    No Known Activations