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

    Neuronpedia

    INDEX
    Explanations

    references to direct interactions or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irtual
    -0.15
     entire
    -0.14
    atics
    -0.14
     tá»Ń
    -0.14
    osis
    -0.14
    ocs
    -0.13
    334
    -0.13
     aloud
    -0.13
    -ending
    -0.13
     distinct
    -0.13
    POSITIVE LOGITS
    direct
    0.18
    -direct
    0.18
    ives
    0.18
    .Direct
    0.17
     direct
    0.17
     DIRECT
    0.16
     directly
    0.15
    Direct
    0.15
    DIRECT
    0.15
    idad
    0.15
    Act Density 0.026%

    No Known Activations