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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     imprecise
    0.84
     totaled
    0.82
     ineffective
    0.77
    ва
    0.77
     decisive
    0.77
     monotonous
    0.75
     vague
    0.75
     unnamed
    0.74
     fervent
    0.74
     inanimate
    0.73
    POSITIVE LOGITS
    вые
    0.76
     &
    0.75
     ,,
    0.75
    㧕
    0.75
    ۸
    0.74
    𝙲
    0.72
    ؍
    0.72
    ۷
    0.71
     argento
    0.71
    ove
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.