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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    abase
    -0.80
    heastern
    -0.79
    heast
    -0.77
    clair
    -0.72
     Puppet
    -0.71
    iera
    -0.70
    umpy
    -0.69
     Arbor
    -0.68
    cyclopedia
    -0.67
    oppy
    -0.67
    POSITIVE LOGITS
    =-=-=-=-
    0.79
     salute
    0.66
     minus
    0.65
     indebted
    0.63
     deduction
    0.63
     promise
    0.62
     Ded
    0.62
     Nad
    0.60
    BLIC
    0.59
     sweat
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.