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

    Neuronpedia

    INDEX
    Explanations

    references to examples or lists in discussions or reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ysz
    -0.16
     Goldberg
    -0.15
     Gy
    -0.15
    -parts
    -0.14
    fat
    -0.14
    ham
    -0.14
     تÙĦÙģ
    -0.14
    ida
    -0.13
    YST
    -0.13
     Flexible
    -0.13
    POSITIVE LOGITS
    askell
    0.14
    æIJº
    0.14
    imson
    0.14
    agoon
    0.14
    vet
    0.14
    anson
    0.14
    acr
    0.14
    'icon
    0.13
     нен
    0.13
     æĬ
    0.13
    Act Density 0.416%

    No Known Activations