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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing gratitude or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express gratitude or appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    apest
    -0.76
    erenn
    -0.75
    emies
    -0.74
    ãĥĥãĥī
    -0.74
    ires
    -0.74
    subject
    -0.72
     denies
    -0.71
    terness
    -0.71
    holm
    -0.69
    zona
    -0.69
    POSITIVE LOGITS
     generous
    1.41
     generosity
    1.18
     ingenuity
    1.14
     clever
    1.14
     diligent
    1.13
     ingenious
    1.12
     persever
    1.06
     donations
    1.05
     concerted
    1.04
     assistance
    1.02
    Act Density 0.321%

    No Known Activations