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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     scalp
    -0.41
     realise
    -0.41
     realising
    -0.39
    KeyDown
    -0.39
     starve
    -0.39
     morale
    -0.38
     advisor
    -0.38
     Pat
    -0.38
    syl
    -0.38
     killer
    -0.38
    POSITIVE LOGITS
    increments
    3.08
     increments
    1.36
    increment
    1.06
     increment
    1.05
     Increment
    1.00
    Incre
    0.99
    INCREMENT
    0.93
    Increment
    0.93
     AssemblyCulture
    0.83
     Incre
    0.81
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.