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

    Neuronpedia

    INDEX
    Explanations

    words related to the concept of impossibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.69
     Sutherland
    -0.68
     Conquer
    -0.66
     Franks
    -0.66
     GEAR
    -0.64
    wald
    -0.63
     Rite
    -0.62
    aurus
    -0.62
     Jenner
    -0.61
     Sins
    -0.61
    POSITIVE LOGITS
    ossible
    1.25
    ossibly
    1.25
    regn
    1.21
    ressive
    1.18
    ressing
    1.18
    otent
    1.10
    ounded
    1.08
    romptu
    1.06
    ressed
    1.05
    ract
    1.03
    Act Density 0.003%

    No Known Activations