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

    Neuronpedia

    INDEX
    Explanations

    specific sequences of characters, especially representations of data, numerical values, or variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    "):
    -1.17
    ']))
    -1.02
    "],
    -1.02
    "];
    -1.00
    "])
    -1.00
    ")));
    -0.98
    $",
    -0.97
     *}$
    -0.97
    "]
    -0.95
    "]);
    -0.95
    POSITIVE LOGITS
     poffible
    1.24
     Monfieur
    1.21
     Diſ
    1.21
     Shakspeare
    1.19
     Cæsar
    1.18
     Reſ
    1.16
     pleaſure
    1.16
     itſelf
    1.15
     greateſt
    1.13
     doubtnut
    1.10
    Act Density 2.874%

    No Known Activations