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

    Neuronpedia

    INDEX
    Explanations

    specific page numbers in a text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific page numbers or citations in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bench
    -0.68
     disposable
    -0.62
     balloon
    -0.61
     cooled
    -0.60
     outgoing
    -0.60
     stead
    -0.60
     Stead
    -0.59
     homegrown
    -0.59
    ones
    -0.59
    LLOW
    -0.58
    POSITIVE LOGITS
     âĨij
    1.06
     ff
    1.04
     seq
    0.90
     NRS
    0.87
    ]).
    0.86
     quoting
    0.86
     footnote
    0.86
     .)
    0.84
     ital
    0.83
    .;
    0.81
    Act Density 0.077%

    No Known Activations