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

    Neuronpedia

    INDEX
    Explanations

    terms related to academic or technical language, particularly in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edin
    -0.15
    aina
    -0.14
    anou
    -0.14
    ffi
    -0.14
    endon
    -0.14
    ootball
    -0.14
    unner
    -0.14
    ouro
    -0.14
    ledon
    -0.14
     iconName
    -0.13
    POSITIVE LOGITS
    ness
    0.20
    287
    0.17
     Exposure
    0.15
    _above
    0.14
    idunt
    0.14
    NESS
    0.14
    rowse
    0.13
     Cable
    0.13
    nosti
    0.13
    ysts
    0.13
    Act Density 0.001%

    No Known Activations