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

    Neuronpedia

    INDEX
    Explanations

    phrases related to project updates or progress reports

    oai_token-act-pair · gpt-3.5-turbo

    the word "our" indicating collective experience or belonging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    conom
    -0.78
    puff
    -0.75
    cum
    -0.72
    ppings
    -0.72
    bender
    -0.72
    ussen
    -0.70
    icter
    -0.69
     appears
    -0.69
    tar
    -0.69
    more
    -0.68
    POSITIVE LOGITS
    selves
    1.20
     own
    1.05
     beloved
    0.93
     motto
    0.87
     ourselves
    0.87
     collective
    0.86
     respective
    0.86
     ancestors
    0.85
     adversaries
    0.83
     dear
    0.83
    Act Density 0.135%

    No Known Activations