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

    Neuronpedia

    INDEX
    Explanations

    punctuation and markers of uncertainty or inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /umd
    -0.17
    ÑĢд
    -0.15
    orp
    -0.15
    ird
    -0.15
    -lite
    -0.15
    bjerg
    -0.14
    vincia
    -0.13
    lsi
    -0.13
    rium
    -0.13
     Flake
    -0.13
    POSITIVE LOGITS
     duty
    0.16
     cez
    0.15
    inus
    0.15
    inea
    0.15
    ema
    0.15
    ooks
    0.15
    icals
    0.14
    ccion
    0.14
    eful
    0.14
     Duty
    0.14
    Act Density 0.012%

    No Known Activations