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

    Neuronpedia

    INDEX
    Explanations

    phrases or conjunctions that list multiple items or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iglia
    -0.17
    arih
    -0.16
    amba
    -0.16
    .scalablytyped
    -0.15
    ------+------+
    -0.14
    txn
    -0.14
    нÑĮ
    -0.14
    ÑĮеÑĢ
    -0.14
    raquo
    -0.14
    allis
    -0.14
    POSITIVE LOGITS
    rough
    0.15
    aber
    0.14
     Sons
    0.14
    izio
    0.14
    ault
    0.14
    abra
    0.13
    apot
    0.13
    pheres
    0.13
    irc
    0.13
    à¹Ģà¸Ħ
    0.13
    Act Density 0.181%

    No Known Activations