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

    Neuronpedia

    INDEX
    Explanations

    references to squares and square-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istrovstvÃŃ
    -0.17
    åľŃ
    -0.17
    591
    -0.16
    957
    -0.16
    955
    -0.15
    пÑĢав
    -0.15
    lesh
    -0.15
    oen
    -0.15
    稱
    -0.15
    590
    -0.14
    POSITIVE LOGITS
    ignum
    0.15
    éĥ
    0.15
    inho
    0.15
     ZemÄĽ
    0.14
    orum
    0.14
    aths
    0.14
    aria
    0.14
    arias
    0.14
    tring
    0.14
    ilim
    0.13
    Act Density 0.010%

    No Known Activations