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

    Neuronpedia

    INDEX
    Explanations

    names of people or entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific entities, particularly related to organizations, locations, and people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ################
    -0.58
    Translation
    -0.57
    %%%%
    -0.57
    ween
    -0.56
    *.
    -0.56
    Ð
    -0.55
    bearing
    -0.55
    twitch
    -0.55
    ̶
    -0.55
    Ò
    -0.54
    POSITIVE LOGITS
     declined
    1.29
     meanwhile
    1.22
     also
    1.17
     spokesman
    1.16
     apologized
    1.13
     echoed
    1.12
     spokeswoman
    1.12
     disagreed
    1.12
     countered
    1.12
     said
    1.11
    Act Density 0.587%

    No Known Activations