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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their placement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stown
    -0.16
    -gnu
    -0.16
    esso
    -0.15
     Rounds
    -0.15
     Leh
    -0.14
    ilio
    -0.14
    round
    -0.14
     Wich
    -0.14
     Hen
    -0.14
     Schwartz
    -0.14
    POSITIVE LOGITS
    ynom
    0.17
    üml
    0.15
     shoot
    0.15
    ارش
    0.14
     Artem
    0.14
    otron
    0.14
    olec
    0.14
    Persist
    0.13
    eer
    0.13
     pathMatch
    0.13
    Act Density 0.009%

    No Known Activations