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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and indicators of excitement or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ston
    -0.16
    iddy
    -0.15
     *)((
    -0.14
    lick
    -0.13
     omin
    -0.13
     jack
    -0.13
     Cave
    -0.13
    isle
    -0.13
     Cout
    -0.13
     groups
    -0.13
    POSITIVE LOGITS
    ossa
    0.18
    uz
    0.17
    ajor
    0.16
    окÑĢема
    0.15
    елиÑĩ
    0.15
    å¼ĭ
    0.15
    оÑĢон
    0.15
    eniz
    0.15
    otal
    0.15
    ç¾½
    0.14
    Act Density 0.010%

    No Known Activations