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

    Neuronpedia

    INDEX
    Explanations

    terms emphasizing inclusion and design within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .dense
    -0.15
    Bracket
    -0.14
    ermann
    -0.14
    emos
    -0.14
     Burns
    -0.14
    èm
    -0.13
    erry
    -0.13
     Rent
    -0.13
    еÑĢжав
    -0.13
    ;\↵
    -0.13
    POSITIVE LOGITS
    iye
    0.16
     Sala
    0.14
    ÙģتÙĩ
    0.14
    dbcTemplate
    0.14
    inded
    0.14
    keiten
    0.14
    زار
    0.13
    alsa
    0.13
     enough
    0.13
    idal
    0.13
    Act Density 0.275%

    No Known Activations