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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating intentions or actions related to improvement and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    utherland
    -0.18
    osi
    -0.16
    erdale
    -0.15
    uluk
    -0.15
    swire
    -0.15
    curacy
    -0.14
    éĽħ
    -0.14
    ìĽĶë¶ĢíĦ°
    -0.14
    (åľŁ
    -0.14
    icity
    -0.14
    POSITIVE LOGITS
    /us
    0.17
    .MM
    0.15
    åª
    0.14
     ãģĹ
    0.14
     Alle
    0.14
    isons
    0.13
    son
    0.13
    ypass
    0.13
    íĪ¬
    0.13
    yster
    0.13
    Act Density 0.084%

    No Known Activations