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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     tomat
    -0.69
    cious
    -0.66
     Dumb
    -0.65
     Prompt
    -0.61
     moaning
    -0.60
    Buff
    -0.60
    artisan
    -0.60
     plaint
    -0.60
     Quartz
    -0.59
     Struggle
    -0.59
    POSITIVE LOGITS
    ascal
    0.64
    ategor
    0.63
    amas
    0.62
     TOTAL
    0.61
    achelor
    0.60
    han
    0.60
    INAL
    0.59
     undisclosed
    0.59
    ovember
    0.59
     clinic
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.