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

    Neuronpedia

    INDEX
    Explanations

    terms related to dimensions in mathematical or physical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ajas
    -0.15
     Harden
    -0.14
    zilla
    -0.14
    нин
    -0.14
    aly
    -0.14
    573
    -0.13
    æĢģ
    -0.13
    rying
    -0.13
    nic
    -0.13
    ähr
    -0.13
    POSITIVE LOGITS
    elsey
    0.15
    Balancer
    0.15
    ãģĸ
    0.14
    dictions
    0.13
    anean
    0.13
    åħ¹
    0.13
    Stripe
    0.13
    ervo
    0.13
    ãĤ¤ãĥī
    0.13
    ceae
    0.13
    Act Density 0.024%

    No Known Activations