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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks that signify speech or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eka
    -0.16
     Evel
    -0.15
    олÑĮно
    -0.15
    otos
    -0.15
    erah
    -0.15
    veled
    -0.15
    ãĥ³ãĤ°
    -0.14
    FTA
    -0.14
    zell
    -0.14
    320
    -0.14
    POSITIVE LOGITS
    elson
    0.15
     Bik
    0.14
    èŃĺ
    0.14
    .binding
    0.14
    estic
    0.14
    prite
    0.14
    ritz
    0.14
     Typed
    0.14
     blackout
    0.14
     Burst
    0.13
    Act Density 0.075%

    No Known Activations