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

    Neuronpedia

    INDEX
    Explanations

    dates specified within parentheses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the open parenthesis symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dazz
    -0.75
     lull
    -0.75
     lax
    -0.73
     nitrogen
    -0.72
     mimic
    -0.69
     breathe
    -0.68
     dro
    -0.68
     shine
    -0.67
     tox
    -0.67
     electr
    -0.67
    POSITIVE LOGITS
    ...)
    1.26
    âĢ¦)
    1.23
    ?)
    1.18
    excluding
    1.14
    credit
    1.11
    sic
    1.11
    see
    1.09
    depending
    1.09
    !)
    1.09
    approximately
    1.08
    Act Density 0.135%

    No Known Activations