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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing a short duration or time period

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "brief."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ceans
    -0.74
    OURCE
    -0.68
    rogens
    -0.67
    apter
    -0.67
    IVER
    -0.66
    obal
    -0.64
    IRO
    -0.64
    20439
    -0.64
    ources
    -0.63
    rees
    -0.62
    POSITIVE LOGITS
    case
    1.50
    cases
    1.42
     stint
    0.98
     glimpse
    0.98
     glimps
    0.94
     resp
    0.93
     foray
    0.91
     interruption
    0.90
    ebin
    0.87
     glance
    0.86
    Act Density 0.048%

    No Known Activations