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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    OWER
    -0.78
    OPS
    -0.76
     Luffy
    -0.75
    Option
    -0.74
    adelphia
    -0.73
    OUGH
    -0.66
    Kids
    -0.65
    UCK
    -0.63
     Saur
    -0.63
     tee
    -0.62
    POSITIVE LOGITS
    comings
    0.82
    vation
    0.77
    hemy
    0.75
    tones
    0.71
    rition
    0.69
    otine
    0.68
    liners
    0.66
     Huang
    0.66
    alyst
    0.65
    ciation
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.