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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ples
    -0.74
     bets
    -0.69
     destro
    -0.69
    gra
    -0.67
    apes
    -0.66
    grave
    -0.66
     oranges
    -0.65
    orius
    -0.64
    aunts
    -0.64
     gamble
    -0.63
    POSITIVE LOGITS
    OND
    0.74
    LAN
    0.71
    CTV
    0.71
    METHOD
    0.70
    ĪĴ
    0.70
    irlf
    0.69
    PLIC
    0.67
    GW
    0.67
    ICA
    0.67
     robust
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.