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

    Neuronpedia

    INDEX
    Explanations

    instances of speaking or discussing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abet
    -0.14
    419
    -0.14
     Burr
    -0.14
    deen
    -0.14
    licit
    -0.13
    ÑĭÑĤ
    -0.13
    Ãļ
    -0.13
    [arg
    -0.13
    when
    -0.13
    loo
    -0.13
    POSITIVE LOGITS
     length
    0.23
    favor
    0.21
     briefly
    0.20
     lengths
    0.20
    length
    0.20
     glow
    0.20
     favor
    0.20
    -length
    0.19
     Candid
    0.19
     lenght
    0.18
    Act Density 0.053%

    No Known Activations