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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate intention or potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    488
    -0.16
    ara
    -0.15
    rick
    -0.15
    ongs
    -0.14
    se
    -0.14
     Kra
    -0.14
    ropy
    -0.14
    ync
    -0.14
    ader
    -0.14
    388
    -0.14
    POSITIVE LOGITS
    寸
    0.16
    iled
    0.16
    hiba
    0.15
    tÄĽ
    0.15
     ë´IJ
    0.14
    ãĥ¼ãĥĩ
    0.14
     EVT
    0.14
     ç©
    0.14
    amet
    0.14
    oard
    0.14
    Act Density 0.038%

    No Known Activations