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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    cheon
    -0.83
    hips
    -0.76
    etically
    -0.72
    iano
    -0.71
    anga
    -0.68
    inav
    -0.67
    ettes
    -0.67
    cano
    -0.66
    inson
    -0.65
    ovie
    -0.64
    POSITIVE LOGITS
    Frames
    0.65
     strand
    0.64
    BUG
    0.63
    CHAT
    0.63
    ¥ŀ
    0.62
    Listener
    0.62
    fram
    0.61
     Huck
    0.60
    fect
    0.59
    joining
    0.59
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.