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

    Neuronpedia

    INDEX
    Explanations

    official statements or actions issued or approved by governmental bodies

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to official actions or decisions by organizations or governmental bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sing
    -0.71
    yond
    -0.70
    been
    -0.69
    cum
    -0.66
    die
    -0.64
    é¾įåĸļ士
    -0.63
    ene
    -0.63
    illary
    -0.62
    isable
    -0.62
    odan
    -0.60
    POSITIVE LOGITS
     unanimously
    0.72
    nesday
    0.66
    nces
    0.65
     yesterday
    0.63
     tentative
    0.62
    Ĥİ
    0.62
     lax
    0.59
     extensively
    0.58
     tremend
    0.58
    arthed
    0.58
    Act Density 0.473%

    No Known Activations