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

    Neuronpedia

    INDEX
    Explanations

    specific numerical values, often in the context of recommendations or functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     interchangeable
    -0.17
    prox
    -0.16
     mb
    -0.15
    urga
    -0.15
    çŃĴ
    -0.15
     uninterrupted
    -0.14
    GLISH
    -0.13
    ix
    -0.13
    olah
    -0.13
    ei
    -0.13
    POSITIVE LOGITS
    enco
    0.16
    amage
    0.15
    reesome
    0.15
    brid
    0.14
    ibbon
    0.14
    libc
    0.14
    leck
    0.14
    ảo
    0.14
    __.__
    0.14
    -lib
    0.14
    Act Density 0.092%

    No Known Activations