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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interaction and activity in a social setting

    oai_token-act-pair · gpt-3.5-turbo

    references to gatherings or events involving groups of people or crowds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Klux
    -0.65
    oslov
    -0.59
    failed
    -0.58
    fell
    -0.52
    rafted
    -0.52
    rugged
    -0.52
    pent
    -0.51
    romy
    -0.51
     vocational
    -0.50
    addafi
    -0.50
    POSITIVE LOGITS
     patiently
    0.68
     caveats
    0.64
     occasionally
    0.64
     wherever
    0.64
     acknowledgement
    0.64
     perpetually
    0.64
     hopefully
    0.63
     preferably
    0.63
     invariably
    0.63
     politely
    0.62
    Act Density 1.103%

    No Known Activations