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

    Neuronpedia

    INDEX
    Explanations

    block comment endings in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hinton
    -0.56
    UnknownFields
    -0.55
    werd
    -0.55
     Whitehead
    -0.54
    mond
    -0.52
    GeneratedCode
    -0.52
    ソッド
    -0.52
    Clik
    -0.51
    vantages
    -0.50
     mua
    -0.48
    POSITIVE LOGITS
     dumne
    0.71
    RegressionTest
    0.63
     الحره
    0.63
    __*/
    0.62
     kasarigan
    0.60
    findpost
    0.59
     CURIAM
    0.59
     correctes
    0.58
     armée
    0.56
     utafitiHapana
    0.56
    Act Density 0.212%

    No Known Activations