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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and body parts

    oai_token-act-pair · gpt-3.5-turbo

    references to personal feelings and societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inventoryQuantity
    -0.72
    cffffcc
    -0.71
    âĢ
    -0.59
    ģ«
    -0.58
    EStreamFrame
    -0.58
    )}
    -0.57
    ¶æ
    -0.55
    _{
    -0.55
    ãĢ
    -0.55
    ãĤ´ãĥ³
    -0.55
    POSITIVE LOGITS
     (£
    0.57
     Wellington
    0.56
     -
    0.55
     Kiw
    0.54
     and
    0.54
     –
    0.54
     recognised
    0.53
     maths
    0.53
     honoured
    0.53
     Adelaide
    0.52
    Act Density 1.301%

    No Known Activations