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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    phinx
    -0.16
     киÑĢ
    -0.15
    ongan
    -0.15
    heim
    -0.15
    hari
    -0.15
     tá»ij
    -0.14
     Garland
    -0.14
    yo
    -0.14
    svc
    -0.14
    ilde
    -0.14
    POSITIVE LOGITS
     Vict
    0.17
    utzer
    0.17
    elay
    0.15
    utron
    0.15
    Mappings
    0.15
     Clover
    0.14
    ichert
    0.14
     Jos
    0.13
     Jac
    0.13
     Summon
    0.13
    Act Density 0.005%

    No Known Activations