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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    rix
    -0.72
    plot
    -0.66
    uten
    -0.66
    rophe
    -0.66
     appre
    -0.66
    iak
    -0.64
    osponsors
    -0.64
     tha
    -0.63
    yll
    -0.63
    estern
    -0.63
    POSITIVE LOGITS
    hyde
    0.74
     preferably
    0.72
    channelAvailability
    0.70
     etc
    0.67
     barring
    0.66
    starting
    0.66
     namely
    0.66
    anwhile
    0.65
     secondly
    0.64
     ensuring
    0.64
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.