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

    Neuronpedia

    INDEX
    Explanations

    words and phrases related to citations and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.18
    ách
    -0.15
    ramid
    -0.15
    abelle
    -0.15
    夢
    -0.14
    彦
    -0.14
    htub
    -0.14
     crushing
    -0.14
    onom
    -0.14
     bpp
    -0.14
    POSITIVE LOGITS
    arkan
    0.17
    gw
    0.15
    lash
    0.14
    adas
    0.14
    PCODE
    0.14
    ób
    0.14
    iyon
    0.14
    .xz
    0.13
    icode
    0.13
    944
    0.13
    Act Density 0.003%

    No Known Activations