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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    yles
    -0.75
    wagen
    -0.72
    roxy
    -0.69
    rpm
    -0.68
    tre
    -0.68
     tyr
    -0.67
    wn
    -0.67
    opian
    -0.67
    ppelin
    -0.66
    appy
    -0.66
    POSITIVE LOGITS
    ãĤ¡
    0.75
     stances
    0.65
    aucuses
    0.65
    lasses
    0.61
     Cond
    0.61
    GU
    0.60
    GF
    0.60
    aepernick
    0.60
     Spur
    0.60
    ãģ¦
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.