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

    Neuronpedia

    INDEX
    Explanations

    references to rankings, listings, or categorization of items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    áh
    -0.15
    ski
    -0.14
    750
    -0.14
    YPD
    -0.14
    enas
    -0.14
     Kop
    -0.14
     Lad
    -0.14
    ÏģοÏħ
    -0.13
    atr
    -0.13
    ifiers
    -0.13
    POSITIVE LOGITS
    ingers
    0.16
    ãĥ³ãĥģ
    0.15
     uncon
    0.15
    uant
    0.14
    isman
    0.14
     Boeh
    0.14
    edor
    0.14
     Startup
    0.13
     DISPATCH
    0.13
    ź
    0.13
    Act Density 0.005%

    No Known Activations