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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    uca
    -0.70
     Flores
    -0.68
    ocol
    -0.68
     Hes
    -0.66
    ombo
    -0.64
     Iw
    -0.63
    olini
    -0.63
    esi
    -0.63
    avis
    -0.62
    INO
    -0.62
    POSITIVE LOGITS
    ihar
    0.83
    endar
    0.72
    OTOS
    0.72
    )].
    0.71
    )))
    0.69
    EVA
    0.69
    der
    0.69
    ntil
    0.69
     retract
    0.68
    ¥µ
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.