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

    Neuronpedia

    INDEX
    Explanations

    references to the superhero character "Wonder Woman."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Wonder Woman"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    escription
    -0.75
     externalToEVAOnly
    -0.73
     destro
    -0.71
    aution
    -0.71
     seiz
    -0.65
     ABE
    -0.65
     manslaughter
    -0.63
     VIDE
    -0.63
     Obj
    -0.63
     disg
    -0.61
    POSITIVE LOGITS
    kid
    1.12
    stru
    1.12
    fully
    1.09
    bolt
    1.07
    ful
    1.06
    FUL
    1.05
    kids
    1.03
    fulness
    1.01
    wall
    0.98
    bol
    0.98
    Act Density 0.037%

    No Known Activations