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

    Neuronpedia

    INDEX
    Explanations

    phrases that contain exceptions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nil
    -0.18
    NIL
    -0.15
     вÑģп
    -0.15
    ç«¥
    -0.15
    unker
    -0.14
    \grid
    -0.14
    nds
    -0.14
    .metro
    -0.14
    isoft
    -0.14
    ãĤ´ãĥª
    -0.14
    POSITIVE LOGITS
     limited
    0.27
    limited
    0.22
     Limited
    0.20
     limitation
    0.20
    Limited
    0.18
     restricted
    0.17
     LIMITED
    0.17
     not
    0.16
    limit
    0.16
     limit
    0.16
    Act Density 0.005%

    No Known Activations