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

    Neuronpedia

    INDEX
    Explanations

    titles or references to installments in a series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ffm
    -0.14
     پس
    -0.14
    325
    -0.14
    oman
    -0.14
     pearls
    -0.13
    253
    -0.13
    EI
    -0.13
     Breakfast
    -0.13
    acket
    -0.13
    asan
    -0.13
    POSITIVE LOGITS
    ByExample
    0.17
    prod
    0.16
    ivec
    0.15
    arl
    0.15
    atu
    0.14
    MENT
    0.14
    block
    0.14
     Freund
    0.14
    _^(
    0.14
    -series
    0.14
    Act Density 0.045%

    No Known Activations