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

    Neuronpedia

    INDEX
    Explanations

    references to national organizations or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ffen
    -0.16
    etas
    -0.15
    infeld
    -0.14
    olina
    -0.13
    ufs
    -0.13
    .experimental
    -0.13
    upert
    -0.13
    ollen
    -0.13
     iceberg
    -0.12
     wir
    -0.12
    POSITIVE LOGITS
    tml
    0.14
    atsby
    0.14
    lant
    0.13
    ãĥĥãĤ·ãĥ¥
    0.13
    лиÑĩ
    0.13
    estroy
    0.13
     UNU
    0.13
    ephir
    0.13
     Stern
    0.13
     PUSH
    0.13
    Act Density 0.120%

    No Known Activations