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

    Neuronpedia

    INDEX
    Explanations

    social media platform mentions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Proced
    -0.62
    uilding
    -0.60
    pit
    -0.59
     Fusion
    -0.58
     stewards
    -0.58
    lav
    -0.58
    uberty
    -0.58
    ĪĴ
    -0.58
     Reborn
    -0.58
     retrospective
    -0.57
    POSITIVE LOGITS
     SHARES
    0.96
     Flavoring
    0.87
    ÙĦ
    0.71
     Whats
    0.67
     WRITE
    0.64
     NET
    0.60
    LIN
    0.59
    à¼
    0.59
     Shares
    0.58
    orie
    0.58
    Act Density 0.023%

    No Known Activations