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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    wic
    -0.64
    aird
    -0.64
    lied
    -0.63
    Flags
    -0.62
     Ryu
    -0.62
    raft
    -0.62
    esy
    -0.62
    etts
    -0.61
     Pier
    -0.61
     typh
    -0.61
    POSITIVE LOGITS
    avid
    0.69
    imeo
    0.65
    ample
    0.64
    idia
    0.62
    avour
    0.61
    CLAIM
    0.60
    framework
    0.60
    andre
    0.60
    committee
    0.59
    itous
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.