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

    Neuronpedia

    INDEX
    Explanations

    expressions of reluctance or avoidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ament
    -0.17
    baugh
    -0.15
    ente
    -0.14
    eam
    -0.14
    ENTE
    -0.14
    meli
    -0.14
    umpt
    -0.14
     outs
    -0.14
    _NM
    -0.14
     Leisure
    -0.14
    POSITIVE LOGITS
     spared
    0.19
     ngại
    0.19
    å¬
    0.17
     çľ
    0.16
     sugar
    0.16
     sparing
    0.16
     minced
    0.15
    çľ
    0.15
    ispers
    0.15
     punches
    0.15
    Act Density 0.059%

    No Known Activations