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

    Neuronpedia

    INDEX
    Explanations

    references to substitution or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     beyond
    -0.17
    323
    -0.16
     Beyond
    -0.14
    ake
    -0.14
     revision
    -0.14
    aro
    -0.14
     Dust
    -0.14
     dust
    -0.14
    nte
    -0.14
    auen
    -0.13
    POSITIVE LOGITS
    .consume
    0.16
    .gdx
    0.16
    imento
    0.16
    IMENT
    0.15
    boxed
    0.14
    ìķĻ
    0.14
    ér
    0.14
    /Branch
    0.14
    htdocs
    0.14
    utable
    0.14
    Act Density 0.020%

    No Known Activations