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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating opposition or disagreement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of opposition or disagreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.78
    ptoms
    -0.74
    abulary
    -0.73
    dden
    -0.72
    krit
    -0.71
    istical
    -0.71
     pione
    -0.70
     partName
    -0.69
    miah
    -0.68
    LAN
    -0.68
    POSITIVE LOGITS
     granting
    1.02
     legalizing
    0.97
     adopting
    0.95
     legalization
    0.94
     allowing
    0.93
     privatization
    0.91
     unilateral
    0.91
     letting
    0.88
     incorporation
    0.88
     any
    0.88
    Act Density 0.149%

    No Known Activations