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

    Neuronpedia

    INDEX
    Explanations

    mentions of the name "Chris" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific names, particularly "Chris" and "Michael"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     P
    -0.83
     D
    -0.83
     Sw
    -0.82
     M
    -0.81
     High
    -0.81
     T
    -0.81
     F
    -0.80
     St
    -0.80
     B
    -0.80
     S
    -0.79
    POSITIVE LOGITS
    Robert
    1.55
    Jake
    1.55
    Sov
    1.54
    Eric
    1.52
    Kevin
    1.52
    Anthony
    1.52
    Richard
    1.51
    James
    1.50
    Jonathan
    1.50
    Ryan
    1.50
    Act Density 0.165%

    No Known Activations