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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    kat
    -0.95
    caster
    -0.77
    RPG
    -0.65
    dule
    -0.65
    dict
    -0.65
    rocket
    -0.64
    casters
    -0.63
     fasting
    -0.63
    ensical
    -0.63
    adian
    -0.62
    POSITIVE LOGITS
    thia
    0.67
     dash
    0.65
    ãĤĵ
    0.65
    idelity
    0.64
     Shapiro
    0.62
     Lt
    0.59
    imilation
    0.59
     intact
    0.59
    ikawa
    0.59
     nuance
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.