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

    Neuronpedia

    INDEX
    Explanations

    terms related to governance and political structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    op
    -0.53
     spéciale
    -0.53
    ev
    -0.49
    C
    -0.48
    S
    -0.47
    Special
    -0.47
    locals
    -0.46
    もと
    -0.46
    ava
    -0.46
    PV
    -0.46
    POSITIVE LOGITS
    orship
    1.18
    ership
    1.04
     ModelExpression
    0.98
    wardship
    0.97
    MergeFrom
    0.96
    TagMode
    0.96
    thood
    0.93
    WriteBarrier
    0.92
     tenancy
    0.89
    RotationOrder
    0.88
    Act Density 0.252%

    No Known Activations