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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ITLE
    -0.15
    chaft
    -0.15
    arton
    -0.15
    lich
    -0.15
    urv
    -0.14
    ourse
    -0.14
    avigate
    -0.14
    psy
    -0.14
    анÑģи
    -0.14
    rovers
    -0.14
    POSITIVE LOGITS
     Joy
    0.19
     Joyce
    0.17
    Joy
    0.17
     Triangle
    0.16
     Joe
    0.16
     Joel
    0.16
    оза
    0.16
     Jose
    0.15
    oloj
    0.15
     jo
    0.15
    Act Density 0.024%

    No Known Activations