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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation that indicate programming syntax or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    >Main
    -0.16
    -heading
    -0.15
     âĨIJ
    -0.15
    isson
    -0.14
    >Nama
    -0.14
    --}}↵
    -0.13
    ocio
    -0.13
    >:</
    -0.13
    lore
    -0.13
    obus
    -0.13
    POSITIVE LOGITS
    >
    0.46
     >
    0.43
    >↵
    0.33
    >manual
    0.32
     >↵
    0.32
    >NN
    0.31
    >,
    0.29
    >equals
    0.29
    >(
    0.28
     >↵↵
    0.27
    Act Density 0.058%

    No Known Activations