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

    Neuronpedia

    INDEX
    Explanations

    phrases related to expansion or growth

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "expand" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MET
    -0.80
    ndra
    -0.77
    mir
    -0.76
    ches
    -0.75
    pee
    -0.74
    lain
    -0.73
    ¢
    -0.72
    nee
    -0.71
    ched
    -0.71
    gu
    -0.70
    POSITIVE LOGITS
    sheets
    0.76
     exponentially
    0.75
     awareness
    0.75
     utilization
    0.75
     explos
    0.75
     outward
    0.74
     enormously
    0.73
     pains
    0.73
     opportunities
    0.72
    onential
    0.71
    Act Density 0.023%

    No Known Activations