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

    Neuronpedia

    INDEX
    Explanations

    specific names or terms related to notable entities, titles, or theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illet
    -0.17
    anki
    -0.14
    RAP
    -0.14
    rese
    -0.14
    .CR
    -0.13
    æ¢
    -0.13
    upo
    -0.13
    ownt
    -0.13
    bilt
    -0.13
    .Misc
    -0.12
    POSITIVE LOGITS
    dorf
    0.15
    θÎŃ
    0.15
     sor
    0.15
     Sor
    0.15
    NAS
    0.14
    nÃŃk
    0.14
    åħį
    0.14
     èij
    0.14
    quine
    0.13
    alien
    0.13
    Act Density 0.233%

    No Known Activations