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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    raught
    -0.70
     tremend
    -0.70
     Skydragon
    -0.64
    overs
    -0.64
     Veronica
    -0.63
     underway
    -0.62
     penchant
    -0.61
     exha
    -0.61
     Niet
    -0.60
     discredited
    -0.60
    POSITIVE LOGITS
    ardless
    0.82
    illion
    0.79
    allas
    0.78
    riad
    0.72
    auri
    0.72
    ambo
    0.69
    inea
    0.68
    abet
    0.68
    illions
    0.67
    ranch
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.