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

    Neuronpedia

    INDEX
    Explanations

    references to "circle" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MenuInflater
    -0.82
    ########.
    -0.80
    +#+
    -0.79
    ntax
    -0.78
     pitié
    -0.74
    owulf
    -0.73
     Fordham
    -0.71
    esModule
    -0.71
    ˏ
    -0.70
     fritas
    -0.70
    POSITIVE LOGITS
     Circle
    2.14
     circle
    2.13
     CIRCLE
    2.10
     circles
    2.07
    Circle
    1.95
     Circles
    1.95
    circle
    1.83
    Circles
    1.81
    CIRCLE
    1.77
    circles
    1.76
    Act Density 0.078%

    No Known Activations