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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ocene
    -0.81
    agen
    -0.72
    urst
    -0.67
    monds
    -0.66
    encing
    -0.65
    archs
    -0.65
    ona
    -0.64
     Pitch
    -0.61
    pton
    -0.60
    arch
    -0.60
    POSITIVE LOGITS
     toget
    0.71
     describ
    0.68
     Aval
    0.66
    ersive
    0.66
    INESS
    0.63
    owship
    0.62
     CET
    0.62
     WARNING
    0.62
     disapp
    0.61
    cffff
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.