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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the number "1" followed by sequences of other digits

    oai_token-act-pair · gpt-3.5-turbo

    numbers in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lumpur
    -0.78
    awaru
    -0.72
    enges
    -0.65
    orative
    -0.65
     hygiene
    -0.64
    espie
    -0.63
    thinkable
    -0.62
    opy
    -0.62
    ategory
    -0.61
    anty
    -0.60
    POSITIVE LOGITS
    Password
    1.37
    125
    1.26
    st
    1.23
    120
    1.22
    ½
    1.06
    128
    1.03
    000000
    1.00
    âģ
    0.92
    123
    0.90
     Corinthians
    0.88
    Act Density 0.104%

    No Known Activations