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

    Neuronpedia

    INDEX
    Explanations

    references to decline in various contexts or sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onCreateView
    -0.75
     polyg
    -0.72
     Hered
    -0.71
     Maddox
    -0.71
     Surreal
    -0.71
     Chiapas
    -0.71
    synthesis
    -0.70
     GenerationType
    -0.70
    omation
    -0.70
     שוליים
    -0.69
    POSITIVE LOGITS
     burden
    0.80
     decline
    0.72
    parsedMessage
    0.65
    ]').
    0.60
     Decline
    0.60
     declines
    0.60
     Burden
    0.60
    ctu
    0.59
    burden
    0.58
    MessageTagHelper
    0.57
    Act Density 0.073%

    No Known Activations