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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the need for additional information or further reading

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upy
    -0.17
    опиÑģ
    -0.16
    eneg
    -0.16
    bob
    -0.15
    tings
    -0.14
    icerca
    -0.14
     motions
    -0.14
    nict
    -0.14
    à¥Ĥद
    -0.14
    ãĢħ
    -0.13
    POSITIVE LOGITS
    mann
    0.15
     fasc
    0.15
     Fasc
    0.15
     Cli
    0.15
    éIJ
    0.14
     Chall
    0.14
    üf
    0.14
    ipi
    0.14
     unb
    0.13
     Mant
    0.13
    Act Density 0.004%

    No Known Activations