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

    Neuronpedia

    INDEX
    Explanations

    references to articles, reports, and statistical data in a structured news context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     honoring
    -0.17
     малÑĮ
    -0.16
    vt
    -0.15
     honors
    -0.15
     Peterson
    -0.15
    innie
    -0.14
     Walsh
    -0.14
     honorable
    -0.14
    .scalablytyped
    -0.14
     resil
    -0.14
    POSITIVE LOGITS
    achi
    0.17
    EPS
    0.17
    abox
    0.15
    anke
    0.14
    .jd
    0.14
    lund
    0.14
    ää
    0.14
    ึ
    0.13
     Freel
    0.13
     Numero
    0.13
    Act Density 0.016%

    No Known Activations