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

    Neuronpedia

    INDEX
    Explanations

    URLs

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific news source or website

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Micro
    -0.65
     forcing
    -0.62
     partition
    -0.61
     insert
    -0.61
     plate
    -0.59
     evolution
    -0.59
     punishing
    -0.59
    ļéĨĴ
    -0.57
     indec
    -0.57
     atomic
    -0.56
    POSITIVE LOGITS
    ws
    4.45
    wed
    2.37
    wt
    1.45
    wd
    1.43
    wn
    1.41
    wy
    1.40
    wl
    1.40
    wic
    1.37
    wi
    1.35
    WS
    1.34
    Act Density 0.014%

    No Known Activations