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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    CP
    -0.72
    762
    -0.70
    CA
    -0.68
    678
    -0.67
    CN
    -0.66
    CW
    -0.66
    776
    -0.66
    RC
    -0.65
    BS
    -0.64
    odon
    -0.63
    POSITIVE LOGITS
    antha
    0.84
    ĸļ
    0.82
    lished
    0.76
    selection
    0.72
    markets
    0.69
     benches
    0.68
    tein
    0.67
    iques
    0.66
    gradation
    0.66
    inoa
    0.66
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.