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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    teness
    -0.68
     brass
    -0.66
     Lank
    -0.65
    odan
    -0.65
    leneck
    -0.64
    Tro
    -0.63
     counter
    -0.63
    wik
    -0.63
     reinforcement
    -0.61
     stren
    -0.60
    POSITIVE LOGITS
    JR
    0.77
    EED
    0.74
    FG
    0.73
    icably
    0.72
    igible
    0.70
    MJ
    0.69
     MPH
    0.67
     Blossom
    0.66
    UV
    0.66
    Picture
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.