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

    Neuronpedia

    INDEX
    Explanations

    parentheses and their usage in mathematical or logical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    [++
    -0.16
    utton
    -0.15
    haul
    -0.15
    ASSES
    -0.14
    oler
    -0.14
     ÑĤÑĢо
    -0.14
    imli
    -0.14
    Ïĥμ
    -0.14
    lit
    -0.14
    hung
    -0.13
    POSITIVE LOGITS
    izzo
    0.17
    icans
    0.15
    ellen
    0.14
    yte
    0.14
    adol
    0.14
    ìĬ¤íĬ¸
    0.14
    apolis
    0.14
    bsp
    0.14
    oxide
    0.14
     اع
    0.14
    Act Density 0.036%

    No Known Activations