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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Strateg
    -0.70
    ihar
    -0.69
     apprentices
    -0.68
     retrospect
    -0.67
     proble
    -0.66
     furthe
    -0.65
    roma
    -0.64
     toughest
    -0.64
     Thom
    -0.63
    amental
    -0.63
    POSITIVE LOGITS
    ãĥķãĤ¡
    0.72
    HUD
    0.72
    leted
    0.72
    poke
    0.72
    liner
    0.71
    Lua
    0.71
    ãĤ¶
    0.70
    969
    0.70
    hash
    0.70
    «ĺ
    0.69
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.