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

    Neuronpedia

    INDEX
    Explanations

    words related to accountability and oversight in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QUAL
    -0.15
    upe
    -0.15
    osu
    -0.15
    enek
    -0.15
    aviest
    -0.14
    å¤
    -0.14
    rq
    -0.14
    èm
    -0.14
    asio
    -0.14
    IZED
    -0.14
    POSITIVE LOGITS
    pz
    0.16
    420
    0.15
    ovaly
    0.15
     by
    0.15
    uguay
    0.15
     Moo
    0.15
    ãĥ«ãĥĪ
    0.15
    ntag
    0.15
    ught
    0.14
    eker
    0.14
    Act Density 0.229%

    No Known Activations