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

    Neuronpedia

    INDEX
    Explanations

    references to academic citations and literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wards
    -0.16
     Princip
    -0.15
    igy
    -0.15
     yourselves
    -0.15
    iership
    -0.14
    ãĥĥ
    -0.14
     podium
    -0.14
     Alive
    -0.14
     Rat
    -0.14
     Butler
    -0.13
    POSITIVE LOGITS
    alore
    0.16
    ropp
    0.15
    ois
    0.15
    ï¼Īå¹³æĪIJ
    0.15
    baar
    0.15
    ëħ
    0.15
    gree
    0.14
    é»
    0.14
    utt
    0.14
    YRO
    0.14
    Act Density 0.004%

    No Known Activations