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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate uncertainty or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¼ãĥ©
    -0.16
    955
    -0.15
     赤
    -0.15
    .appspot
    -0.14
    ÄĽle
    -0.14
    iode
    -0.14
    iele
    -0.14
    ãĤ
    -0.14
    STYPE
    -0.14
    âĢ¦↵↵↵
    -0.14
    POSITIVE LOGITS
    ernel
    0.16
    fbe
    0.15
    ãĥ³ãĥĹ
    0.14
    _lift
    0.14
    воÑĢÑİ
    0.13
    neys
    0.13
    amp
    0.12
     crossorigin
    0.12
    Brains
    0.12
    _ISR
    0.12
    Act Density 0.212%

    No Known Activations