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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ``
    -0.83
    `.
    -0.80
     destro
    -0.72
    ICLE
    -0.71
    `
    -0.70
     surv
    -0.67
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
    ãĤ¡
    -0.67
    earch
    -0.67
    inav
    -0.65
    POSITIVE LOGITS
     —
    1.58
    —
    1.23
    —"
    1.23
    )—
    1.00
     ÂŃ
    0.95
     âĢķ
    0.93
     Getty
    0.84
     –
    0.84
    .—
    0.84
     --
    0.75
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.