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

    Neuronpedia

    INDEX
    Explanations

    occurrences of proper nouns and significant numerical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qli
    -0.15
    à¥Ģफ
    -0.15
     undef
    -0.15
    ÙĨÙħ
    -0.15
    ühl
    -0.14
    squ
    -0.14
     Blowjob
    -0.14
     Fak
    -0.14
    ivant
    -0.14
    enko
    -0.14
    POSITIVE LOGITS
     Pink
    0.15
    adil
    0.14
    avr
    0.14
    278
    0.14
     r
    0.14
    870
    0.13
     Guerr
    0.13
    #__
    0.13
    ropa
    0.13
    mare
    0.13
    Act Density 0.001%

    No Known Activations