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

    Neuronpedia

    INDEX
    Explanations

    sequences of numbers and symbols in a specific order

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numerical values, particularly those that indicate lists or increments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gathering
    -0.64
    uggest
    -0.64
    Executive
    -0.61
     estimating
    -0.60
     sponsoring
    -0.59
    bda
    -0.58
     manufacturing
    -0.57
    assis
    -0.56
     palpable
    -0.56
    creat
    -0.54
    POSITIVE LOGITS
     etc
    0.99
    etc
    0.97
    ĪĴ
    0.78
     respectively
    0.73
    illance
    0.70
    opt
    0.68
    âĢ¦)
    0.65
     parentheses
    0.65
    ...)
    0.65
    Shift
    0.63
    Act Density 0.136%

    No Known Activations