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

    Neuronpedia

    INDEX
    Explanations

    instances of list or array notation in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.71
     gynhyrchwyd
    -0.68
    }(
    -0.61
    >>(
    -0.60
    >(</
    -0.59
    <>(
    -0.59
    }<
    -0.59
    ↵
    -0.57
    ecin
    -0.57
    )<
    -0.57
    POSITIVE LOGITS
     ["
    1.80
     ['
    1.77
    (["
    1.76
    (['
    1.66
    =['
    1.64
    =["
    1.60
    ',['
    1.34
    :['
    1.33
    ["
    1.31
    [['
    1.28
    Act Density 0.419%

    No Known Activations