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

    Neuronpedia

    INDEX
    Explanations

    references to commands and instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pst
    -0.16
     Clips
    -0.14
     Polic
    -0.14
    ajar
    -0.13
     Flam
    -0.13
    -
    -0.13
    ÏĦι
    -0.13
    ajas
    -0.13
     Monitoring
    -0.13
     seal
    -0.13
    POSITIVE LOGITS
    nad
    0.17
    gili
    0.15
    Å¡ka
    0.15
    iyim
    0.15
    kiye
    0.14
    chaft
    0.14
    ottie
    0.14
    ihad
    0.14
    wend
    0.14
    amu
    0.14
    Act Density 0.083%

    No Known Activations