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

    Neuronpedia

    INDEX
    Explanations

    strong emphasis or certainty

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the absence or lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    len
    -0.60
     Route
    -0.58
     Alzheimer
    -0.56
     late
    -0.54
     Push
    -0.53
     Early
    -0.52
    pa
    -0.52
     Road
    -0.51
     Bronze
    -0.51
     Late
    -0.51
    POSITIVE LOGITS
     whatsoever
    3.97
    soever
    1.66
     whatever
    1.13
     imaginable
    1.11
     EVER
    1.10
    whatever
    1.06
    theless
    0.99
     slightest
    0.97
    withstanding
    0.97
    omever
    0.95
    Act Density 0.015%

    No Known Activations