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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "full" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "full" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    errors
    -0.69
    Wars
    -0.68
     whis
    -0.68
     Royale
    -0.68
    Hop
    -0.67
     Disciple
    -0.66
     Phi
    -0.66
     Guys
    -0.66
    artifacts
    -0.66
    gemony
    -0.65
    POSITIVE LOGITS
     complement
    0.95
     blown
    0.95
     fled
    0.93
    erton
    0.93
    hearted
    0.87
     sized
    0.86
     frontal
    0.84
     slate
    0.81
     extent
    0.80
    heartedly
    0.79
    Act Density 0.023%

    No Known Activations