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

    Neuronpedia

    INDEX
    Explanations

    references to social structures and their complexities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jer
    -0.15
     Traverse
    -0.14
     warm
    -0.14
    rai
    -0.14
     bill
    -0.14
     riff
    -0.14
     Domino
    -0.14
     pom
    -0.14
     Tem
    -0.14
     Bowling
    -0.13
    POSITIVE LOGITS
     Rig
    0.28
     Ved
    0.25
     Bra
    0.22
     bra
    0.22
     ÅĽ
    0.21
     Santana
    0.21
     Bri
    0.21
     dv
    0.20
     ved
    0.20
     Åļ
    0.20
    Act Density 0.167%

    No Known Activations