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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and formatting in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uppe
    -0.16
    ubits
    -0.15
     деÑĢ
    -0.14
    ÏģÏħ
    -0.14
    ardo
    -0.14
    uty
    -0.14
    umont
    -0.14
    award
    -0.13
     Mur
    -0.13
    spin
    -0.13
    POSITIVE LOGITS
    озÑı
    0.16
    oney
    0.15
    UD
    0.14
    essel
    0.14
     catapult
    0.14
    rig
    0.13
    Ãłi
    0.13
    (always
    0.13
    .constructor
    0.13
    _cust
    0.13
    Act Density 0.001%

    No Known Activations