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

    Neuronpedia

    INDEX
    Explanations

    references to recurring themes or frameworks, particularly regarding patterns and traditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.87
     Geiſt
    -0.84
     utafitiHapana
    -0.81
    <unused3>
    -0.80
    ########.
    -0.80
    <unused74>
    -0.80
    <unused79>
    -0.80
    <unused42>
    -0.80
    [@BOS@]
    -0.80
    <unused41>
    -0.80
    POSITIVE LOGITS
     Culture
    0.73
     culture
    0.71
     Constitution
    0.62
     pattern
    0.60
    Culture
    0.58
    culture
    0.57
     tradition
    0.56
     constitution
    0.53
    Environment
    0.50
     CULTURE
    0.48
    Act Density 0.273%

    No Known Activations