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

    Neuronpedia

    INDEX
    Explanations

    verbs related to the act of stirring or agitation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    лиÑĩ
    -0.18
    undra
    -0.17
    upertino
    -0.17
    kova
    -0.16
    wayne
    -0.15
     Zur
    -0.15
    ertz
    -0.15
    falls
    -0.14
    ersistence
    -0.14
    opers
    -0.14
    POSITIVE LOGITS
    atore
    0.21
    εÏį
    0.18
     stir
    0.18
     stirred
    0.17
    klad
    0.16
     clockwise
    0.15
    antes
    0.15
    ož
    0.15
     Stir
    0.15
    -handed
    0.15
    Act Density 0.016%

    No Known Activations