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

    Neuronpedia

    INDEX
    Explanations

    references to different classes, especially in a legal or regulatory context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     stump
    -0.75
     wit
    -0.73
    OPLE
    -0.71
    hiba
    -0.63
    aukee
    -0.62
     spur
    -0.61
    foreseen
    -0.61
     Bay
    -0.58
     spare
    -0.58
    WT
    -0.57
    POSITIVE LOGITS
    ifications
    1.41
    ifiers
    1.28
    ifier
    1.23
    ifying
    1.21
    ifies
    1.18
    ifiable
    1.13
    ically
    1.09
    ified
    1.08
    mates
    1.01
    ification
    1.00
    Act Density 0.015%

    No Known Activations