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

    Neuronpedia

    INDEX
    Explanations

    verbs that indicate actions or states, particularly in relation to events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤĽ
    -0.17
    OOM
    -0.15
    ãģ¾ãģĽ
    -0.15
    æĻ´
    -0.14
    Å¡i
    -0.14
    ouch
    -0.14
    ordan
    -0.14
    à¹Ģà¸ĭà¸Ńร
    -0.14
    ÑĢÑĥк
    -0.13
    lassen
    -0.13
    POSITIVE LOGITS
     Sant
    0.15
     Ros
    0.15
     accordingly
    0.15
    má
    0.14
    amp
    0.14
    ABI
    0.14
     Magazine
    0.14
     Sta
    0.14
    Ros
    0.14
     apl
    0.14
    Act Density 0.243%

    No Known Activations