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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or terms that indicate relationship to data or documents within a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucher
    -0.18
     ActiveForm
    -0.16
    uben
    -0.15
    úmero
    -0.15
    urette
    -0.15
    abus
    -0.14
    emale
    -0.14
    illage
    -0.14
    illez
    -0.14
    uevo
    -0.14
    POSITIVE LOGITS
    ym
    0.17
     whole
    0.16
    YM
    0.14
    whole
    0.14
     Crop
    0.14
    Crop
    0.14
    856
    0.14
    MING
    0.14
    vana
    0.14
    ITICAL
    0.13
    Act Density 0.001%

    No Known Activations