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

    Neuronpedia

    INDEX
    Explanations

    technological terms and concepts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     reconc
    -0.74
    ecause
    -0.73
    irtual
    -0.72
    drawn
    -0.70
    urion
    -0.65
    lest
    -0.65
    exclusive
    -0.63
    ranch
    -0.62
    actionDate
    -0.62
    nown
    -0.62
    POSITIVE LOGITS
    Ø©
    1.02
    ÏĤ
    0.97
     Ð
    0.94
     ÙĪ
    0.88
    utics
    0.87
     è£ıç
    0.86
    0.85
     srfAttach
    0.84
    и
    0.84
    н
    0.83
    Act Density 0.080%

    No Known Activations