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

    Neuronpedia

    INDEX
    Explanations

    expressions of self-identification and calls for participation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Lug
    -0.14
     Bookmark
    -0.14
     Consort
    -0.14
    bable
    -0.14
    861
    -0.14
    peer
    -0.14
    .codes
    -0.13
     Goldberg
    -0.13
    ergus
    -0.13
    Peer
    -0.13
    POSITIVE LOGITS
    urve
    0.17
    ajor
    0.15
     ham
    0.15
    ãĥĥãĥĪ
    0.15
     ther
    0.14
     spare
    0.14
    ÑĬ
    0.14
    otron
    0.13
    ÂĢÂ
    0.13
     Nixon
    0.13
    Act Density 0.025%

    No Known Activations