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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a comparison of size or value

    oai_token-act-pair · gpt-3.5-turbo

    the term "relatively" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tein
    -0.76
    ved
    -0.73
    osis
    -0.73
     Polo
    -0.72
    HAEL
    -0.71
    ieu
    -0.69
    rea
    -0.68
    ertodd
    -0.66
    amide
    -0.66
    onis
    -0.65
    POSITIVE LOGITS
     tame
    1.11
     unpop
    1.10
     harmless
    1.07
     inexpensive
    1.04
     insignificant
    1.03
     innocuous
    1.03
     benign
    1.00
     speaking
    0.94
     uncont
    0.93
     unaffected
    0.91
    Act Density 0.037%

    No Known Activations