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

    Neuronpedia

    INDEX
    Explanations

    statements expressing personal beliefs or affiliations

    oai_token-act-pair · gpt-3.5-turbo

    statements of personal identity and political beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ©
    -0.71
    idges
    -0.69
    ¥ŀ
    -0.65
    ufact
    -0.64
     accelerated
    -0.61
     favourable
    -0.61
     scrimmage
    -0.60
     satell
    -0.60
     conclud
    -0.60
     adolesc
    -0.59
    POSITIVE LOGITS
     I
    1.62
    I
    1.39
     myself
    1.17
     My
    1.14
     my
    1.09
     Honestly
    1.00
    My
    1.00
    my
    0.86
     II
    0.85
     frankly
    0.85
    Act Density 0.408%

    No Known Activations