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

    Neuronpedia

    INDEX
    Explanations

    references to named data entities or parameters in a coding context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phan
    -0.16
    phen
    -0.16
     phen
    -0.16
    каÑģ
    -0.15
    fant
    -0.15
    pta
    -0.15
    /assert
    -0.14
    gio
    -0.14
    ffi
    -0.14
    bserv
    -0.14
    POSITIVE LOGITS
    eneg
    0.17
    ucci
    0.17
    zem
    0.15
    teÅŁ
    0.14
     intim
    0.14
     shar
    0.14
     tep
    0.14
    atel
    0.13
     haya
    0.13
    oubles
    0.13
    Act Density 0.006%

    No Known Activations