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

    Neuronpedia

    INDEX
    Explanations

    references to statistical analysis software

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.78
     وتسجيلات
    -0.76
     Roskov
    -0.75
     متعلقه
    -0.74
     فريبيس
    -0.72
    ')";
    -0.71
    esez
    -0.70
    })*/
    -0.69
    enumii
    -0.68
    %)$
    -0.68
    POSITIVE LOGITS
     Prism
    0.83
    Prism
    0.67
     CURIAM
    0.50
     Cruel
    0.49
     prism
    0.48
     Obispo
    0.44
     cruel
    0.43
    ToFit
    0.41
    δω
    0.41
     SLO
    0.40
    Act Density 0.001%

    No Known Activations