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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    quality
    -0.76
    inent
    -0.76
     fidelity
    -0.69
    ewitness
    -0.69
    attribute
    -0.68
    cientious
    -0.67
    rov
    -0.66
    icted
    -0.65
    lly
    -0.65
    reating
    -0.64
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    0.90
     ILCS
    0.86
    é¾įå
    0.78
    ¶ħ
    0.73
    Offline
    0.72
    ;;;;;;;;
    0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.71
    ONT
    0.70
    æµ
    0.70
    天
    0.70
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.