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

    Neuronpedia

    INDEX
    Explanations

    information related to changes or actions being taken by different individuals or entities

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used to connect phrases or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onga
    -0.79
    NULL
    -0.73
    ãĥķãĤ¡
    -0.71
    yip
    -0.70
    antz
    -0.69
    existent
    -0.67
    iba
    -0.65
    click
    -0.64
    ital
    -0.64
    merga
    -0.62
    POSITIVE LOGITS
     began
    1.24
     became
    1.22
     proceeded
    1.20
     drove
    1.17
     gave
    1.15
     flew
    1.14
     oversaw
    1.13
     sank
    1.11
     took
    1.11
     stayed
    1.10
    Act Density 0.354%

    No Known Activations