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

    Neuronpedia

    INDEX
    Explanations

    keywords indicating support or approval of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating support or approval for a proposal or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.80
    umbai
    -0.71
     typo
    -0.67
    ĸļ
    -0.64
    venants
    -0.64
    æ©Ł
    -0.64
     teased
    -0.64
    semble
    -0.63
     explodes
    -0.63
     thereafter
    -0.63
    POSITIVE LOGITS
     whichever
    0.84
     underdog
    0.82
     incumb
    0.82
    asty
    0.78
     Remain
    0.77
     legalizing
    0.74
     legalization
    0.72
     caution
    0.70
    itism
    0.70
     indef
    0.70
    Act Density 0.146%

    No Known Activations