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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "done" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ted
    -0.20
    een
    -0.17
    scape
    -0.17
    gen
    -0.17
    s
    -0.17
    csi
    -0.17
    teen
    -0.17
    ti
    -0.16
    teil
    -0.16
    genesis
    -0.16
    POSITIVE LOGITS
    etwork
    0.20
    ecessary
    0.19
    alysis
    0.19
    ed
    0.18
    Ø©
    0.18
    exus
    0.18
    etics
    0.17
    avigator
    0.17
    erals
    0.17
    ails
    0.17
    Act Density 0.132%

    No Known Activations