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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikel
    -0.17
    uble
    -0.15
    emit
    -0.15
    ille
    -0.14
    elan
    -0.14
    ub
    -0.13
    azes
    -0.13
    (ob
    -0.13
     Karl
    -0.13
    iled
    -0.13
    POSITIVE LOGITS
    illance
    0.17
    lech
    0.17
    asz
    0.15
    ¹Ħ
    0.15
    afone
    0.15
    ibri
    0.15
    leston
    0.15
    alars
    0.14
     Randall
    0.14
    utow
    0.14
    Act Density 1.289%

    No Known Activations