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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    phia
    -0.76
     Objective
    -0.66
    chester
    -0.66
    utic
    -0.65
    fed
    -0.65
     Osc
    -0.65
     cosmetic
    -0.64
     Prest
    -0.64
     Percy
    -0.62
     Mission
    -0.62
    POSITIVE LOGITS
     confir
    0.79
    kefeller
    0.67
     destro
    0.67
    ilater
    0.66
     arrang
    0.66
     hepat
    0.66
     answ
    0.65
    bg
    0.64
    icken
    0.64
    bly
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.