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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Calculator
    -0.71
    utterstock
    -0.69
     pedals
    -0.67
    elvet
    -0.65
     Jakarta
    -0.65
    udd
    -0.63
    ernandez
    -0.62
    gra
    -0.62
     presets
    -0.61
     Syndrome
    -0.60
    POSITIVE LOGITS
    ¶æ
    0.69
    endi
    0.68
    Progress
    0.63
     Chairman
    0.59
     lawy
    0.59
    Lua
    0.59
    yond
    0.59
     upwards
    0.59
     laps
    0.59
     neglig
    0.58
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.