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

    Neuronpedia

    INDEX
    Explanations

    references to the number three or groups of three

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    両
    -0.17
    opp
    -0.17
     twins
    -0.15
    nd
    -0.15
     ëijĺ
    -0.15
    cdecl
    -0.14
    æĻ´
    -0.14
    /generated
    -0.14
    area
    -0.14
    urb
    -0.14
    POSITIVE LOGITS
    rd
    0.26
     ä¸ī
    0.20
     trio
    0.20
     Trio
    0.19
     Triple
    0.18
    -quarters
    0.18
    Triple
    0.18
     Three
    0.18
     triple
    0.18
    fold
    0.17
    Act Density 0.376%

    No Known Activations