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

    Neuronpedia

    INDEX
    Explanations

    references to collaborative efforts and social dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olu
    -0.17
    IRR
    -0.15
    §
    -0.14
    tos
    -0.14
     Merchant
    -0.14
    _AND
    -0.14
    imoto
    -0.14
    orna
    -0.13
     Which
    -0.13
    onso
    -0.13
    POSITIVE LOGITS
    —the
    0.18
    rou
    0.16
    olle
    0.16
    -the
    0.15
     Lambert
    0.15
    )this
    0.14
    elastic
    0.14
    ),
    0.14
    -The
    0.14
    -it
    0.14
    Act Density 0.029%

    No Known Activations