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

    Neuronpedia

    INDEX
    Explanations

    character sequences that involve escape characters or formatting in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -1.00
    Gos
    -0.82
     Goose
    -0.79
    goose
    -0.79
     goose
    -0.75
    дь
    -0.71
     wireType
    -0.71
    TokenNameLBRACE
    -0.70
    WriteTagHelper
    -0.70
    Goose
    -0.70
    POSITIVE LOGITS
    ("\
    1.30
    <<"\
    1.29
    ('\
    1.27
    "\
    1.26
     "\
    1.24
    '\
    1.16
    ="\
    1.15
     '\
    1.15
    ,'\
    1.14
    ,"\
    1.12
    Act Density 0.094%

    No Known Activations