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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Labs
    -0.67
    Availability
    -0.66
    yx
    -0.64
    ARS
    -0.62
    ouched
    -0.61
    intend
    -0.60
    BU
    -0.59
     clad
    -0.59
     Seconds
    -0.59
     paws
    -0.59
    POSITIVE LOGITS
    £ı
    0.81
    00200000
    0.74
     mosqu
    0.74
    unity
    0.66
     grape
    0.66
     convol
    0.65
    senal
    0.64
    message
    0.62
    etheless
    0.61
     nuisance
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.