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

    Neuronpedia

    INDEX
    Explanations

    discussions about loyalty and alliances within conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lace
    -0.15
    duc
    -0.15
    orc
    -0.15
    tle
    -0.14
    IFI
    -0.14
    bard
    -0.14
    ensen
    -0.14
    olio
    -0.14
    ologne
    -0.14
     Replies
    -0.13
    POSITIVE LOGITS
     sided
    0.44
     side
    0.43
     siding
    0.42
     sides
    0.40
     Side
    0.36
    side
    0.36
    -side
    0.36
    Side
    0.34
    -sided
    0.33
    _side
    0.32
    Act Density 0.202%

    No Known Activations