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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ez
    -0.74
    hon
    -0.64
    MD
    -0.62
    #$
    -0.61
     eagle
    -0.59
    dry
    -0.59
    ï¸
    -0.59
     Issa
    -0.58
    di
    -0.58
     gastro
    -0.58
    POSITIVE LOGITS
    iband
    0.75
    acci
    0.73
     regress
    0.71
    juries
    0.69
    anding
    0.63
    istration
    0.62
    umer
    0.62
    mite
    0.61
    ittle
    0.61
    izer
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.