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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    OHN
    -0.70
    CHAT
    -0.68
    oin
    -0.67
    iflower
    -0.65
    successfully
    -0.64
    NetMessage
    -0.64
    trace
    -0.64
    iPhone
    -0.63
    Pink
    -0.63
    FIR
    -0.62
    POSITIVE LOGITS
    ãĥ¼ãĥĨ
    0.75
    uese
    0.64
    elson
    0.64
    uitous
    0.64
    zn
    0.64
     extraord
    0.62
     Caucasus
    0.60
     lows
    0.59
    urches
    0.59
     Middle
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.