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

    Neuronpedia

    INDEX
    Explanations

    references to categorical variables in statistical analyses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    categorical classifications and statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pembangunan
    -0.47
     محفوظة
    -0.45
     poffe
    -0.44
     onPostExecute
    -0.44
     himſelf
    -0.44
     reír
    -0.41
     deuda
    -0.41
     insomnia
    -0.41
     Moscú
    -0.41
     Manusia
    -0.40
    POSITIVE LOGITS
     categorical
    1.91
    categorical
    1.82
     Categor
    1.68
    Categor
    1.60
     categorically
    1.25
    categor
    1.24
     categor
    1.16
     catég
    1.13
    ategor
    1.05
     categorize
    1.01
    Act Density 0.013%

    No Known Activations