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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     vestiges
    0.78
     concerted
    0.76
    ુ
    0.76
     forceful
    0.75
     hypothesized
    0.71
     fictitious
    0.71
     regioni
    0.71
     occupant
    0.71
     emotive
    0.69
     foothold
    0.69
    POSITIVE LOGITS
    ar
    1.01
    م
    1.00
    ᒪ
    0.91
    ти
    0.90
    al
    0.89
    ला
    0.88
    Cread
    0.88
    🅔
    0.86
     Flüss
    0.85
    or
    0.84
    Act Density 0.000%

    No Known Activations