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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "circle" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +#+
    -0.86
    ########.
    -0.81
     pitié
    -0.79
    MenuInflater
    -0.78
    ˏ
    -0.76
    ntax
    -0.74
    niest
    -0.73
     fritas
    -0.72
    owulf
    -0.72
    etheless
    -0.72
    POSITIVE LOGITS
     Circle
    1.92
     circle
    1.90
     CIRCLE
    1.90
     circles
    1.87
    Circle
    1.78
     Circles
    1.73
    circle
    1.69
    Circles
    1.67
    CIRCLE
    1.60
    circles
    1.59
    Act Density 0.089%

    No Known Activations