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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ĸļ
    -0.83
    ©¶æ
    -0.74
     drained
    -0.65
     swapped
    -0.62
     beaten
    -0.62
    utsche
    -0.60
    gamer
    -0.60
    acket
    -0.60
     Pound
    -0.59
    ointed
    -0.59
    POSITIVE LOGITS
     Cosponsors
    1.02
    eor
    0.69
    arial
    0.65
    ERY
    0.64
    doms
    0.64
    arius
    0.63
    UF
    0.62
    ylene
    0.62
    wo
    0.62
    =#
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.