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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistical results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    oa̍t
    -0.86
     autorytatywna
    -0.72
    extAlignment
    -0.67
    GEBURTSDATUM
    -0.65
    SourceChecksum
    -0.62
     >=",
    -0.61
     EnglishChoose
    -0.60
     doigt
    -0.60
     CURIAM
    -0.59
    aronne
    -0.59
    POSITIVE LOGITS
     concentrate
    0.59
     concentration
    0.50
    념
    0.48
     impostor
    0.46
     photoshoot
    0.46
    kmale
    0.45
     DBNull
    0.45
    ColumnHeaders
    0.45
    何より
    0.45
    concentr
    0.44
    Act Density 0.095%

    No Known Activations