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

    Neuronpedia

    INDEX
    Explanations

    ellipses indicating omitted text or portions of a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .LayoutStyle
    -0.16
    ittle
    -0.15
    spir
    -0.14
     Weiss
    -0.14
    NE
    -0.14
     Preserve
    -0.14
    ää
    -0.14
    smouth
    -0.13
    rors
    -0.13
    ady
    -0.13
    POSITIVE LOGITS
    yna
    0.17
    arty
    0.17
    airy
    0.15
    aleigh
    0.14
    LOAT
    0.14
    IRST
    0.14
    enburg
    0.14
    ecz
    0.14
    YTE
    0.14
    aab
    0.14
    Act Density 0.005%

    No Known Activations