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

    Neuronpedia

    INDEX
    Explanations

    the beginning of documents or significant sections within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    COUVER
    -0.69
    béco
    -0.67
    DNEY
    -0.62
    rrggbb
    -0.59
    orteur
    -0.59
     SYDNEY
    -0.54
    ksjoner
    -0.52
    cipar
    -0.51
     Honolulu
    -0.51
    rungsseite
    -0.51
    POSITIVE LOGITS
    findpost
    0.59
    moor
    0.55
    InlineData
    0.53
    publicain
    0.51
     stok
    0.50
    }{*}{}
    0.50
    stock
    0.50
     consistency
    0.49
     betweenstory
    0.49
     wic
    0.48
    Act Density 0.155%

    No Known Activations