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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas and periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ationToken
    -0.16
    ijken
    -0.15
    ase
    -0.15
    itan
    -0.14
    ught
    -0.14
    arging
    -0.13
    Æ°
    -0.13
    ogle
    -0.13
    sst
    -0.13
    ³
    -0.13
    POSITIVE LOGITS
    ervas
    0.17
    ContextHolder
    0.15
    ££
    0.14
    osi
    0.14
    anford
    0.13
    /lists
    0.13
    umbed
    0.13
    ze
    0.13
     Render
    0.13
    ndern
    0.13
    Act Density 0.007%

    No Known Activations