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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to effective parameters and efficiency in a scientific context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     <=",
    -1.16
    MigrationBuilder
    -0.98
    +#+#
    -0.72
    PerformLayout
    -0.70
    RegressionTest
    -0.69
    ?}",
    -0.68
    -0.68
    RetentionPolicy
    -0.68
    numerusform
    -0.66
    ]-->
    -0.66
    POSITIVE LOGITS
    Altri
    0.58
     HX
    0.58
    neſs
    0.52
    GHIJKLM
    0.52
     lda
    0.50
    icionar
    0.49
     sandero
    0.49
     Jad
    0.49
     dafs
    0.49
    ating
    0.48
    Act Density 0.032%

    No Known Activations