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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    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
     retaliation
    -0.65
     immunity
    -0.64
     retali
    -0.64
    )].
    -0.62
     spurious
    -0.62
     bogus
    -0.62
     prosecutions
    -0.62
     intrusion
    -0.61
     withdrawal
    -0.61
     dep
    -0.60
    POSITIVE LOGITS
    ĸļ
    0.75
    acci
    0.71
     âĿ
    0.67
    erella
    0.67
    iverse
    0.64
    nesday
    0.64
    Gaming
    0.63
    ̶
    0.61
    âĸ¬
    0.61
    etsy
    0.60
    Act Density 1.625%

    No Known Activations