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

    Neuronpedia

    INDEX
    Explanations

    references to bars or similar establishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    bar tableau, barbies, barracuda, baristas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Toussaint
    -0.50
    <>
    -0.50
    offensive
    -0.49
    geni
    -0.44
    ^)
    -0.44
    ede
    -0.43
    ete
    -0.43
    mitten
    -0.43
    unes
    -0.43
    este
    -0.43
    POSITIVE LOGITS
     bar
    1.59
     Bar
    1.32
     bars
    1.13
    bar
    1.13
    Bar
    1.13
     BAR
    1.06
    Bars
    0.96
     Bars
    0.96
    BAR
    0.94
    bars
    0.93
    Act Density 0.028%

    No Known Activations