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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "done."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roller
    -0.17
    ÙĩÙħ
    -0.17
    craft
    -0.17
    mente
    -0.17
    ly
    -0.17
    ted
    -0.17
    ship
    -0.16
    doch
    -0.16
    rette
    -0.16
    side
    -0.16
    POSITIVE LOGITS
    pez
    0.25
    -done
    0.19
    actic
    0.19
    zo
    0.18
    hower
    0.17
    exion
    0.17
     justice
    0.16
    erts
    0.15
     deal
    0.15
    cket
    0.15
    Act Density 0.030%

    No Known Activations