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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate positional relationships or spatial arrangement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erras
    -0.17
    ÑĢел
    -0.16
    aghan
    -0.16
    antino
    -0.15
    quier
    -0.14
    iale
    -0.14
    ovna
    -0.14
    anova
    -0.14
    ãĥ«ãĤ¯
    -0.14
    สà¸ĩ
    -0.14
    POSITIVE LOGITS
     Suff
    0.17
    arm
    0.15
    lang
    0.14
    ::__
    0.14
    ÃŃ
    0.14
    ways
    0.14
    427
    0.14
    ÑģпÑĸлÑĮ
    0.14
    fo
    0.14
    904
    0.14
    Act Density 0.025%

    No Known Activations