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

    Neuronpedia

    INDEX
    Explanations

    references to high-profile legal or ethical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ä»
    -0.16
    ãĤ¤ãĤ¹
    -0.15
    oms
    -0.15
     t
    -0.15
    iso
    -0.15
     αÏĥ
    -0.14
    anners
    -0.14
    моÑģ
    -0.14
     sty
    -0.14
     Fargo
    -0.14
    POSITIVE LOGITS
    jedn
    0.15
    êµ´
    0.15
    uler
    0.15
     OMIT
    0.14
    PEND
    0.14
    efe
    0.14
    quip
    0.14
    eam
    0.14
    .rpc
    0.14
    eed
    0.14
    Act Density 0.049%

    No Known Activations