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

    Neuronpedia

    INDEX
    Explanations

    references to historical and influential figures and their contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     varsa
    -0.09
     various
    -0.08
     GOODMAN
    -0.08
    inati
    -0.08
     Various
    -0.08
    íħIJ
    -0.08
     оÑĤли
    -0.08
    iddi
    -0.07
    celik
    -0.07
    éĥİ
    -0.07
    POSITIVE LOGITS
     rather
    0.12
     instead
    0.11
     actually
    0.10
     none
    0.09
     neither
    0.09
     Rather
    0.09
     not
    0.08
    rather
    0.08
     entirely
    0.08
     something
    0.08
    Act Density 0.045%

    No Known Activations