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

    Neuronpedia

    INDEX
    Explanations

    specific phrases or terms related to political or social events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize prominence or significance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udence
    -0.70
    rade
    -0.70
    zai
    -0.69
    iety
    -0.69
    icho
    -0.69
    iterator
    -0.68
    cohol
    -0.67
    han
    -0.65
    gae
    -0.65
    lich
    -0.63
    POSITIVE LOGITS
     brunt
    1.39
     lion
    1.35
     reins
    1.28
     mantle
    1.24
     blame
    1.23
     spo
    1.17
     bulk
    1.16
     spotlight
    1.12
     majority
    1.07
     slack
    1.06
    Act Density 0.209%

    No Known Activations