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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    }>{
    0.89
    ч
    0.84
    ([\
    0.82
    intent
    0.82
    "><?
    0.77
     Clicking
    0.76
    探し
    0.75
    black
    0.74
     Heated
    0.73
    Learning
    0.71
    POSITIVE LOGITS
    ે
    1.08
     rev
    1.05
     fueran
    1.01
     మీద
    0.95
     strat
    0.95
     beings
    0.95
     начала
    0.94
    iour
    0.94
     substit
    0.94
    lir
    0.93
    Act Density 0.000%

    No Known Activations