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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "addition" and similar transitional phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mites
    -0.42
    ╝
    -0.42
    glEnd
    -0.40
    cologist
    -0.40
    UDE
    -0.39
    SuccessListener
    -0.38
    OP
    -0.38
    பு
    -0.38
    cru
    -0.38
    rave
    -0.37
    POSITIVE LOGITS
     kasarigan
    0.74
     EconPapers
    0.64
    aarrggbb
    0.64
     utafitiHapana
    0.63
    出版年
    0.60
    +#+#
    0.60
     transfieras
    0.55
     propOrder
    0.55
    theoremstyle
    0.54
     estekak
    0.54
    Act Density 0.096%

    No Known Activations