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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     PLUS
    -0.73
     FSA
    -0.66
    uti
    -0.66
    psey
    -0.65
    unte
    -0.63
    Corp
    -0.63
    uten
    -0.63
    WAR
    -0.62
     pledges
    -0.62
     stret
    -0.62
    POSITIVE LOGITS
    ACTED
    0.75
    ophy
    0.72
    PsyNetMessage
    0.71
    abase
    0.65
    ¥µ
    0.63
    ĸļ
    0.63
    onomy
    0.62
    ĺħ
    0.61
    ims
    0.61
     Angle
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.