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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rough
    -0.69
    knit
    -0.69
    ritch
    -0.66
    omorph
    -0.65
    shi
    -0.64
    ONT
    -0.64
    cest
    -0.64
    idden
    -0.62
    accompanied
    -0.62
    nance
    -0.62
    POSITIVE LOGITS
    .'"
    0.62
     Cir
    0.61
    !'"
    0.61
    rod
    0.60
     commercials
    0.59
     Celeb
    0.59
    devices
    0.59
    heny
    0.58
     Dragonbound
    0.58
     showc
    0.57
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.