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

    Neuronpedia

    INDEX
    Explanations

    auxiliary and modal verbs indicating possibility, necessity, and condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¬ãĥ¼
    -0.14
    oni
    -0.14
    erti
    -0.14
    Fu
    -0.14
     Marty
    -0.13
     hip
    -0.13
    HEET
    -0.13
    icont
    -0.13
    vé
    -0.13
    ëĭĪëĭ¤
    -0.13
    POSITIVE LOGITS
    emoc
    0.16
    ÙĪست
    0.15
    nP
    0.15
    gra
    0.15
    RIES
    0.14
    bjerg
    0.14
    ÙĨب
    0.14
    iliation
    0.14
    acent
    0.14
    ocs
    0.14
    Act Density 0.007%

    No Known Activations