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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     crates
    -0.76
    ¶ħ
    -0.75
     crow
    -0.74
     subsequ
    -0.73
     pudding
    -0.72
     duct
    -0.72
     appropri
    -0.71
     pul
    -0.71
    apy
    -0.71
     plaus
    -0.68
    POSITIVE LOGITS
    emphasis
    0.86
    Cast
    0.85
    NAT
    0.85
    July
    0.84
    Fel
    0.81
    same
    0.81
    Ranked
    0.80
    Irish
    0.80
    Ireland
    0.79
    hitting
    0.79
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.