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

    Neuronpedia

    INDEX
    Explanations

    references to academic or instructional materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ones
    -0.15
     i
    -0.14
     hor
    -0.14
     Stat
    -0.14
     Congress
    -0.13
     lax
    -0.13
    998
    -0.13
    .dex
    -0.13
     And
    -0.13
     Sel
    -0.13
    POSITIVE LOGITS
    iggers
    0.16
    hte
    0.15
    elerik
    0.15
    cba
    0.14
     dne
    0.14
    à¹Īำ
    0.14
    ogle
    0.14
    ìĿ¼ìĹIJ
    0.14
    é«ĺæ¸ħ
    0.13
    Gener
    0.13
    Act Density 0.157%

    No Known Activations