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

    Neuronpedia

    INDEX
    Explanations

    references to theoretical concepts and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itude
    -0.19
    ello
    -0.17
    itan
    -0.16
     theor
    -0.16
    OUR
    -0.16
     teor
    -0.16
    åĪ¶åº¦
    -0.16
    own
    -0.16
    umd
    -0.16
    né
    -0.15
    POSITIVE LOGITS
    rence
    0.19
    /model
    0.17
    ical
    0.17
    /pr
    0.17
    ically
    0.17
    سÛĮÙĨ
    0.16
    /do
    0.16
    /method
    0.16
    craft
    0.16
     dõi
    0.16
    Act Density 0.030%

    No Known Activations