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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    antine
    -0.75
     sacrific
    -0.74
    Story
    -0.71
     seiz
    -0.62
     horm
    -0.62
     misinterpret
    -0.59
    assad
    -0.59
    EH
    -0.59
     stru
    -0.58
    making
    -0.58
    POSITIVE LOGITS
    umn
    0.77
    roo
    0.75
    uther
    0.68
    igham
    0.67
    hots
    0.66
     è£ıè¦ļéĨĴ
    0.65
     Kear
    0.63
    ayette
    0.63
    ${
    0.62
     Rhode
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.