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

    Neuronpedia

    INDEX
    Explanations

    terms related to statistical estimation techniques

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     prediction
    -0.90
    Prediction
    -0.84
     predict
    -0.84
     approximate
    -0.81
     Prediction
    -0.79
    PRED
    -0.78
     socc
    -0.78
    predict
    -0.72
     PRED
    -0.72
    rough
    -0.71
    POSITIVE LOGITS
    hasMoreElements
    0.85
     lenker
    0.68
    AutoScaleMode
    0.65
     Referential
    0.63
    Referencias
    0.62
    fpm
    0.62
    ędziesz
    0.61
     jspb
    0.61
     للاسماء
    0.60
    "><?=
    0.59
    Act Density 0.026%

    No Known Activations