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

    Neuronpedia

    INDEX
    Explanations

    verb forms that indicate states or actions, particularly focusing on present and past forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Loaded
    -0.16
    TAIL
    -0.16
     Loaded
    -0.15
    ENO
    -0.15
     اطÙĦ
    -0.15
    olet
    -0.14
     pregnant
    -0.14
    æ´ģ
    -0.14
    ervas
    -0.14
    iá»ĥu
    -0.13
    POSITIVE LOGITS
     accomplished
    0.33
     done
    0.29
     possible
    0.28
     achieved
    0.27
    possible
    0.25
    done
    0.23
     ham
    0.23
     hinder
    0.23
     via
    0.23
    via
    0.22
    Act Density 0.271%

    No Known Activations