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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    人
    -0.75
    ìĿ
    -0.70
    ATURES
    -0.69
    Ñĭ
    -0.67
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.66
     todd
    -0.66
    ¬¼
    -0.66
    imeo
    -0.65
    éĹ
    -0.64
    inki
    -0.64
    POSITIVE LOGITS
    nostic
    0.72
    bable
    0.68
    urat
    0.64
     Nish
    0.63
    rer
    0.60
     Bots
    0.59
    odan
    0.59
    ernandez
    0.58
     narrow
    0.58
    apeshifter
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.