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

    Neuronpedia

    INDEX
    Explanations

    instances of emphasis or significant quantities in a text, particularly numeric or mathematical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ůl
    -0.17
    örü
    -0.16
    irc
    -0.15
    rand
    -0.15
    asje
    -0.15
    ÐľÐŀ
    -0.15
    DUCT
    -0.14
    Ø·ØŃ
    -0.14
    iously
    -0.14
    nev
    -0.14
    POSITIVE LOGITS
     labor
    0.15
     Corn
    0.15
     æ²
    0.14
     Labor
    0.13
    Qualifier
    0.13
    adow
    0.13
    ĭ
    0.13
     Boss
    0.13
     Sag
    0.13
    ulus
    0.13
    Act Density 0.003%

    No Known Activations