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

    Neuronpedia

    INDEX
    Explanations

    references to arms and arm-related terminology

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    alty
    -0.75
    %)$
    -0.74
     McDaniel
    -0.69
     Kunt
    -0.68
     INSPECTION
    -0.67
    ↓
    -0.67
    Inspection
    -0.66
     resourceCulture
    -0.66
     gj
    -0.66
     Thurman
    -0.66
    POSITIVE LOGITS
     Arm
    1.48
     arm
    1.45
     arms
    1.41
     ARM
    1.39
    Arm
    1.38
     Arms
    1.34
    arm
    1.25
     braço
    1.17
    Arms
    1.16
     braccio
    1.11
    Act Density 0.016%

    No Known Activations