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

    Neuronpedia

    INDEX
    Explanations

    phrases related to limitations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ³ķ人
    -0.17
    unker
    -0.16
    nil
    -0.16
    .metro
    -0.16
    isoft
    -0.16
    vr
    -0.15
    ãĤ´ãĥª
    -0.15
    emes
    -0.15
    chied
    -0.14
     вÑģп
    -0.14
    POSITIVE LOGITS
     not
    0.25
     limited
    0.22
     limitation
    0.21
    limited
    0.19
    éĻIJ
    0.18
    ä¸įæĺ¯
    0.17
    udo
    0.17
     limit
    0.17
     Limited
    0.17
    limit
    0.17
    Act Density 0.007%

    No Known Activations