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

    Neuronpedia

    INDEX
    Explanations

    instances where something is missing or was missed

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "miss" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vec
    -0.66
     independently
    -0.64
    oran
    -0.64
    lee
    -0.62
     anecd
    -0.61
    iov
    -0.59
    iol
    -0.59
    CLA
    -0.57
    gemony
    -0.57
     Continued
    -0.57
    POSITIVE LOGITS
    pelled
    1.29
    pell
    1.26
    peak
    1.18
    poke
    1.18
    pelling
    1.09
     deadlines
    1.08
     opportunities
    1.07
    pent
    1.02
    hap
    0.99
     opportunity
    0.95
    Act Density 0.080%

    No Known Activations