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

    Neuronpedia

    INDEX
    Explanations

    sequences of backslashes and quotes in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.89
    WriteTagHelper
    -0.87
     Godt
    -0.79
    mybatisplus
    -0.77
    Holt
    -0.74
    ########.
    -0.73
     Langford
    -0.73
    basa
    -0.72
     osc
    -0.72
    YNC
    -0.72
    POSITIVE LOGITS
    ("\
    1.52
     "\
    1.49
    "\
    1.47
    <<"\
    1.41
    ,"\
    1.35
    ('\
    1.29
    ="\
    1.28
     '\
    1.19
     ("\
    1.17
    '\
    1.13
    Act Density 0.162%

    No Known Activations