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

    Neuronpedia

    INDEX
    Explanations

    terms related to the process of decoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grim
    -0.16
    sock
    -0.15
    gaard
    -0.15
    ueur
    -0.14
    ulen
    -0.14
    uguay
    -0.14
    reo
    -0.14
    ugh
    -0.14
    reh
    -0.14
     Commonwealth
    -0.14
    POSITIVE LOGITS
    /import
    0.15
    urre
    0.15
    æ¯į
    0.14
     cap
    0.14
    çħ§
    0.14
    irs
    0.14
    ÑĢан
    0.13
    ["$
    0.13
    eler
    0.13
    umd
    0.13
    Act Density 0.009%

    No Known Activations