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

    Neuronpedia

    INDEX
    Explanations

    words associated with the concept of "cruelty" or "harshness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bew
    -0.73
     plomb
    -0.59
     Fuß
    -0.58
    ardo
    -0.58
    losis
    -0.54
     Frau
    -0.53
     vj
    -0.53
    fand
    -0.53
    AxisAlignment
    -0.52
    abus
    -0.52
    POSITIVE LOGITS
     propOrder
    0.79
     Cr
    0.77
     CR
    0.76
     cref
    0.74
     kasarigan
    0.72
    MigrationBuilder
    0.70
    CR
    0.69
     Cri
    0.68
    craw
    0.67
    Cru
    0.66
    Act Density 0.159%

    No Known Activations