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

    Neuronpedia

    INDEX
    Explanations

    frequently used common words and phrases indicating existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agli
    -0.18
    edik
    -0.16
     Erotik
    -0.15
    Ĭ
    -0.15
    BLE
    -0.15
    Burn
    -0.14
    lek
    -0.14
    pped
    -0.14
    bib
    -0.14
    hari
    -0.14
    POSITIVE LOGITS
    auce
    0.16
    ÏĦιν
    0.16
     anywhere
    0.15
    053
    0.15
    fillna
    0.15
    ancy
    0.14
    anes
    0.13
    774
    0.13
    rogen
    0.13
    venta
    0.13
    Act Density 0.001%

    No Known Activations