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

    Neuronpedia

    INDEX
    Explanations

    statistical measures and performance metrics related to diagnostic tests and model evaluation

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    IVEREF
    -0.83
     ComVisible
    -0.81
    -0.81
    AddTagHelper
    -0.75
    }))
    -0.73
    DeleteBehavior
    -0.71
    KommentareTeilen
    -0.70
     estekak
    -0.69
     '\\;'
    -0.68
    Демографія
    -0.67
    POSITIVE LOGITS
    overall
    0.51
    polator
    0.49
     overall
    0.48
     typical
    0.48
     B
    0.46
     total
    0.46
     Typical
    0.46
     average
    0.46
    korb
    0.46
    average
    0.44
    Act Density 0.261%

    No Known Activations