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

    Neuronpedia

    INDEX
    Explanations

    personal and opinionated statements along with Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    sentiments related to personal connections and events involving family or friends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĢij
    -0.80
    Table
    -0.69
     dependence
    -0.69
    ãĤ¨ãĥ«
    -0.67
    ©¶æ¥µ
    -0.67
    —
    -0.66
    ø
    -0.63
     eighteen
    -0.63
    ,—
    -0.63
    âĪĴ
    -0.62
    POSITIVE LOGITS
    ï¸ı
    1.18
     @
    1.18
     congr
    0.98
     ðŁ
    0.98
     Dems
    0.96
    OTUS
    0.94
     #
    0.93
     tweets
    0.91
     ðŁij
    0.90
    sic
    0.90
    Act Density 0.345%

    No Known Activations