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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    psons
    -0.81
    issance
    -0.80
    poons
    -0.75
    uble
    -0.75
    én
    -0.75
     gems
    -0.74
     comprom
    -0.70
    vertisement
    -0.69
     sentient
    -0.69
    poon
    -0.69
    POSITIVE LOGITS
     iso
    0.79
    IDA
    0.72
     correction
    0.66
    ia
    0.63
     Viet
    0.63
     Liberia
    0.62
    IA
    0.62
    cmp
    0.61
    ij
    0.60
    Box
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.