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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    trap
    -0.76
    ultimate
    -0.72
    selves
    -0.71
     Sorceress
    -0.71
    bags
    -0.70
    NF
    -0.69
     Gutenberg
    -0.69
    handler
    -0.69
     Effective
    -0.68
    Effective
    -0.66
    POSITIVE LOGITS
     shudder
    0.76
    olia
    0.72
    itus
    0.71
    entious
    0.70
    ornia
    0.68
     nostalgia
    0.67
     Rye
    0.67
    rones
    0.65
     adm
    0.64
    ges
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.