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

    Neuronpedia

    INDEX
    Explanations

    function declarations and method calls in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <unused8>
    -1.31
    [@BOS@]
    -1.31
    <unused28>
    -1.31
    <unused79>
    -1.31
    <unused41>
    -1.31
    <unused43>
    -1.30
    <unused51>
    -1.30
    <unused42>
    -1.30
    <unused3>
    -1.30
    <unused14>
    -1.30
    POSITIVE LOGITS
    __
    0.39
    _
    0.30
    「
    0.28
    。
    0.27
     της
    0.26
    的
    0.25
    >("
    0.25
     _
    0.25
    <unused61>
    0.25
    @
    0.25
    Act Density 0.696%

    No Known Activations