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

    Neuronpedia

    INDEX
    Explanations

    references to "classic" items or themes in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thing
    -0.16
    ost
    -0.15
    oken
    -0.14
     (
    -0.13
    -0.13
    ÑĤе
    -0.13
    ¬
    -0.13
    agen
    -0.13
    iding
    -0.13
    ego
    -0.13
    POSITIVE LOGITS
     ogs
    0.16
    otas
    0.16
    AllWindows
    0.15
    /simple
    0.15
    ardy
    0.14
    forme
    0.14
    /original
    0.14
    lime
    0.14
    rieg
    0.14
    kova
    0.14
    Act Density 0.016%

    No Known Activations