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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    heads
    -0.75
    light
    -0.71
    lights
    -0.71
    unk
    -0.70
    jit
    -0.70
    inks
    -0.68
    apter
    -0.67
     LEDs
    -0.67
    oys
    -0.63
    ories
    -0.63
    POSITIVE LOGITS
    encers
    0.79
    encer
    0.77
    ascade
    0.73
     Arkansas
    0.72
     glac
    0.71
     subsequ
    0.67
     Bret
    0.65
    cipled
    0.65
    wikipedia
    0.64
    gypt
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.