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

    Neuronpedia

    INDEX
    Explanations

    numeric values or measurements expressed in a specific format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RegressionTest
    -1.02
    WriteLiteral
    -1.00
     Fargo
    -0.93
     Paxton
    -0.93
    Vos
    -0.89
     Moseley
    -0.87
    posia
    -0.87
    pasta
    -0.86
    nodoc
    -0.85
    *~*~
    -0.85
    POSITIVE LOGITS
    1.08
    1.06
    1.02
    0.94
    0.93
    </i>
    0.84
    iarkan
    0.84
    Grü
    0.81
    0.76
    grü
    0.76
    Act Density 0.038%

    No Known Activations