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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     actionGroup
    -0.81
    osite
    -0.79
    soType
    -0.74
     )]
    -0.71
    Ô
    -0.69
     rall
    -0.68
    ussen
    -0.68
    án
    -0.65
    phal
    -0.65
    OPA
    -0.65
    POSITIVE LOGITS
    tiny
    0.76
    ugar
    0.71
     acre
    0.67
     cubic
    0.66
    pox
    0.66
    heter
    0.65
     bucks
    0.64
    ede
    0.64
    profits
    0.64
    ishy
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.