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

    Neuronpedia

    INDEX
    Explanations

    verbs and actions denoting changes, manipulations, or enforcement of rules and laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     indeb
    -0.15
    lotte
    -0.15
    uran
    -0.15
    èģĶç½ij
    -0.14
    esthetic
    -0.14
    IEW
    -0.14
    Interpolator
    -0.14
    .Creator
    -0.14
    leness
    -0.13
     Gibbs
    -0.13
    POSITIVE LOGITS
    ed
    0.26
    edBy
    0.26
    stered
    0.18
    ized
    0.18
    eted
    0.18
    ised
    0.17
    edException
    0.17
    ován
    0.17
    ified
    0.16
    ãģķãĤĮ
    0.16
    Act Density 0.124%

    No Known Activations