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

    Neuronpedia

    INDEX
    Explanations

    expressions of regret or negative outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    438
    -0.16
    ught
    -0.14
    ighton
    -0.14
    427
    -0.14
    iblings
    -0.14
    agedList
    -0.14
    aldi
    -0.14
    Äįe
    -0.14
    Äįka
    -0.14
    pectives
    -0.13
    POSITIVE LOGITS
     none
    0.21
    ably
    0.20
    antly
    0.19
     timed
    0.19
     Timing
    0.17
    omas
    0.16
     timing
    0.16
     enough
    0.16
    none
    0.16
    lest
    0.15
    Act Density 0.021%

    No Known Activations