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

    Neuronpedia

    INDEX
    Explanations

    perks or benefits

    oai_token-act-pair · gpt-3.5-turbo

    terms related to benefits and bonuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izen
    -0.66
    ago
    -0.65
    chin
    -0.65
    ordered
    -0.64
    ppo
    -0.63
    iverpool
    -0.63
    ichen
    -0.62
    hibition
    -0.61
     Hurricanes
    -0.60
    cled
    -0.59
    POSITIVE LOGITS
     perk
    1.42
     perks
    1.39
     bonus
    0.84
     challeng
    0.83
     recip
    0.80
    onomic
    0.79
    laus
    0.79
     quirks
    0.79
    icka
    0.78
     bonuses
    0.76
    Act Density 0.012%

    No Known Activations