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

    Neuronpedia

    INDEX
    Explanations

    terms related to pivoting or swiveling mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    swivel or pivot actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mData
    -0.46
     requ
    -0.43
     Loi
    -0.42
    alanta
    -0.41
     ан
    -0.40
     Ago
    -0.39
    皆
    -0.39
    ffff
    -0.39
     Angeles
    -0.39
     imma
    -0.38
    POSITIVE LOGITS
     swivel
    1.99
    Swi
    1.30
    ivel
    1.23
     Sw
    0.73
     rotate
    0.68
     Rotating
    0.66
     feroit
    0.66
    Swish
    0.65
     rotates
    0.65
    Sw
    0.63
    Act Density 0.003%

    No Known Activations