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

    Neuronpedia

    INDEX
    Explanations

    structure identifiers and elements related to programming or code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     civilización
    -0.53
     rodillas
    -0.52
    ↵
    -0.48
     paixão
    -0.48
     orejas
    -0.47
     cejas
    -0.46
     Verhandlungen
    -0.46
     península
    -0.46
      
    -0.45
     niebla
    -0.44
    POSITIVE LOGITS
    <unused52>
    1.62
    <unused8>
    1.61
    <unused14>
    1.61
    <unused79>
    1.61
    [@BOS@]
    1.61
    <unused51>
    1.60
    <unused68>
    1.60
    <unused28>
    1.60
    <unused3>
    1.59
    <unused16>
    1.59
    Act Density 1.564%

    No Known Activations