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

    Neuronpedia

    INDEX
    Explanations

    references to cups and their various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,:);
    -0.79
    ']);
    -0.78
    '],$
    -0.75
    )++;
    -0.72
    nois
    -0.72
    %"),
    -0.71
    '])
    -0.71
    equalsIgnoreCase
    -0.70
    ()]
    -0.69
    riwal
    -0.69
    POSITIVE LOGITS
     cup
    2.58
     cups
    2.51
     Cup
    2.49
     Cups
    2.36
     CUP
    2.32
    cup
    2.26
    Cup
    2.20
    cups
    1.95
    CUP
    1.87
    杯
    1.44
    Act Density 0.029%

    No Known Activations