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

    Neuronpedia

    INDEX
    Explanations

    phrases or references to specific phases of projects or studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IPH
    -0.16
     Bilim
    -0.15
    aggio
    -0.15
    ropp
    -0.14
    lady
    -0.14
    VN
    -0.14
    414
    -0.14
    æ±
    -0.13
    á»ĵng
    -0.13
    ucc
    -0.13
    POSITIVE LOGITS
    971
    0.15
     Euler
    0.14
    692
    0.14
    974
    0.14
    bor
    0.14
    ugins
    0.14
    PRINTF
    0.14
    quette
    0.14
     Nug
    0.14
    ugin
    0.13
    Act Density 0.012%

    No Known Activations