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

    Neuronpedia

    INDEX
    Explanations

    sentences stating beliefs or truths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rt
    -0.15
    ewe
    -0.15
     Grim
    -0.15
    ãĥĥãĥĪ
    -0.15
    enic
    -0.15
    itness
    -0.14
    usra
    -0.14
     Jord
    -0.14
    gger
    -0.13
     Monad
    -0.13
    POSITIVE LOGITS
    htub
    0.17
     Affero
    0.14
    ç¶ļ
    0.14
    @update
    0.13
    ARGET
    0.13
    ource
    0.13
    OMPI
    0.13
    ÙĤرار
    0.13
    okino
    0.13
    .bunifuFlatButton
    0.13
    Act Density 0.066%

    No Known Activations