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

    Neuronpedia

    INDEX
    Explanations

    significant names and terms related to recognition and awards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns, especially personal names and institutional names.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Negative Logits
     “
    -0.76
     ‘
    -0.66
     
    -0.60
     at
    -0.60
     "
    -0.59
     des
    -0.56
     -
    -0.56
    .
    -0.54
     (
    -0.54
     tax
    -0.54
    POSITIVE LOGITS
     Efq
    1.48
     Monfieur
    1.31
     Majefty
    1.26
     Theſe
    1.21
     myſelf
    1.16
     Jefus
    1.13
    ſelf
    1.12
    ՚
    1.12
     himſelf
    1.11
     itſelf
    1.10
    Act Density 0.157%

    No Known Activations