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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conjunctions and connections between ideas or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    TD
    -0.14
    Guard
    -0.14
     Jarvis
    -0.14
    rape
    -0.14
    usi
    -0.13
    ldr
    -0.13
    pedia
    -0.13
    taj
    -0.13
    LO
    -0.13
    ird
    -0.13
    POSITIVE LOGITS
     there
    0.17
    aken
    0.16
    bracht
    0.15
    there
    0.14
    abet
    0.14
    Ú©Ø´
    0.14
    pla
    0.13
    à¹Ģà¸Ĺ
    0.13
    (fabs
    0.13
     episodes
    0.13
    Act Density 0.128%

    No Known Activations