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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to decisions and actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal and governmental actions or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !.
    -0.75
    +.
    -0.68
    !:
    -0.65
     sqor
    -0.63
    TPPStreamerBot
    -0.62
    .ãĢį
    -0.61
    isse
    -0.61
    inis
    -0.60
    !,
    -0.60
     respectively
    -0.59
    POSITIVE LOGITS
     amounted
    1.09
     could
    0.90
     stemmed
    0.87
     originated
    0.86
     constitutes
    0.84
     exists
    0.84
     was
    0.84
     outweigh
    0.84
     represents
    0.84
     should
    0.83
    Act Density 0.471%

    No Known Activations