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

    Neuronpedia

    INDEX
    Explanations

    terms and concepts related to binary data and programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    752
    -0.21
    برÛĮ
    -0.16
    wards
    -0.16
    ewater
    -0.15
    ible
    -0.15
    iar
    -0.15
    -quarters
    -0.15
    ried
    -0.15
    roperties
    -0.14
    ord
    -0.14
    POSITIVE LOGITS
    _crossentropy
    0.22
     Laden
    0.21
    /octet
    0.21
    omial
    0.21
    SearchTree
    0.19
    ocular
    0.18
    ity
    0.16
    ogy
    0.16
    -binary
    0.15
    aries
    0.15
    Act Density 0.014%

    No Known Activations