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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or labels within technical documents

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    INGHAM
    -0.52
    </h5>
    -0.44
    </s>
    -0.44
    eche
    -0.44
    paged
    -0.43
    IOUS
    -0.43
    ridged
    -0.43
    ,:]
    -0.43
    ymal
    -0.42
     Schach
    -0.42
    POSITIVE LOGITS
     ***!
    0.84
    InjectAttribute
    0.82
     Infórmanos
    0.79
    adaptiveStyles
    0.75
    RegressionTest
    0.71
    UnsafeEnabled
    0.71
     wikipagina
    0.69
    EDEFAULT
    0.69
     للاسماء
    0.67
    withIdentifier
    0.67
    Act Density 0.237%

    No Known Activations