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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "circle" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.80
    iibo
    -0.74
    tingham
    -0.72
    Anson
    -0.70
     pitié
    -0.68
    InstanceState
    -0.67
    nsics
    -0.65
     Fordham
    -0.65
     Schick
    -0.65
    titudine
    -0.65
    POSITIVE LOGITS
     circle
    2.85
     Circle
    2.74
     circles
    2.65
    Circle
    2.59
     CIRCLE
    2.55
    circle
    2.49
     Circles
    2.40
    circles
    2.21
    CIRCLE
    2.20
    Circles
    2.10
    Act Density 0.074%

    No Known Activations