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

    Neuronpedia

    INDEX
    Explanations

    themes related to socio-political criticism and power dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uple
    -0.16
    eyen
    -0.16
    ore
    -0.14
    ASP
    -0.14
     Affero
    -0.14
     dur
    -0.14
     details
    -0.14
    odic
    -0.14
     so
    -0.14
     ft
    -0.14
    POSITIVE LOGITS
    adÃŃ
    0.21
    agal
    0.19
    .protobuf
    0.14
     plá
    0.14
    acho
    0.14
    дейÑģÑĤв
    0.14
    631
    0.14
    tolower
    0.14
    infeld
    0.13
    ázÃŃ
    0.13
    Act Density 0.490%

    No Known Activations