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

    Neuronpedia

    INDEX
    Explanations

    occurrences of structured or formatted data elements, likely in the context of programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    an
    -1.02
    in
    -0.93
    <b>
    -0.86
    le
    -0.86
    \
    -0.86
    U
    -0.79
    on
    -0.78
    -
    -0.78
    R
    -0.77
    N
    -0.77
    POSITIVE LOGITS
     {}
    1.96
    {}
    1.75
    :{}
    1.64
     {}
    1.55
    ("{}
    1.55
     {};
    1.48
     "{}
    1.46
     {},
    1.46
     &___
    1.44
    ={}
    1.40
    Act Density 0.217%

    No Known Activations