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

    Neuronpedia

    INDEX
    Explanations

    terms related to classification and categorization

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     stump
    -0.68
    hiba
    -0.68
    aukee
    -0.67
     wit
    -0.66
    foreseen
    -0.63
    SIGN
    -0.62
     spur
    -0.62
    OPLE
    -0.60
    edia
    -0.59
    ²¾
    -0.59
    POSITIVE LOGITS
    ifications
    1.39
    ifiers
    1.30
    ifier
    1.29
    ifies
    1.21
    ifying
    1.20
    ifiable
    1.08
    ification
    1.02
    ified
    1.02
    ically
    1.01
    mates
    0.93
    Act Density 0.528%

    No Known Activations