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

    Neuronpedia

    INDEX
    Explanations

    references to academic or technical sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ern
    -0.17
    éIJµ
    -0.14
    ervo
    -0.14
    atted
    -0.14
    rego
    -0.14
    enberg
    -0.14
    iete
    -0.14
    ãĥ¼ãĥį
    -0.13
    DBG
    -0.13
    .Server
    -0.13
    POSITIVE LOGITS
    aines
    0.16
    hoot
    0.15
    ø
    0.14
    Rejected
    0.14
    DirectoryName
    0.14
    =wx
    0.14
    hab
    0.14
    äl
    0.14
     descent
    0.14
    amb
    0.14
    Act Density 0.082%

    No Known Activations