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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude or relief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intensive
    -0.73
    umes
    -0.68
    amental
    -0.68
    igate
    -0.62
    soever
    -0.62
     inappropriately
    -0.61
     hotly
    -0.60
     excessively
    -0.60
    urst
    -0.60
    abus
    -0.60
    POSITIVE LOGITS
     survived
    1.17
     spared
    1.08
     escaped
    0.98
     overcame
    0.90
     managed
    0.88
     saved
    0.87
     luckily
    0.87
    reen
    0.85
     intervened
    0.84
     survives
    0.84
    Act Density 0.326%

    No Known Activations