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

    Neuronpedia

    INDEX
    Explanations

    phrases that highlight significant societal changes or accomplishments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    duk
    -0.15
    ensen
    -0.15
    sert
    -0.14
    anded
    -0.14
    immel
    -0.13
    emen
    -0.13
    orph
    -0.13
    -0.13
    ENSE
    -0.13
     keyst
    -0.13
    POSITIVE LOGITS
     happening
    0.23
     happens
    0.20
     happened
    0.19
     happen
    0.18
    burger
    0.17
     done
    0.17
     aconte
    0.17
     accomplished
    0.17
     Done
    0.16
    vang
    0.16
    Act Density 0.091%

    No Known Activations