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

    Neuronpedia

    INDEX
    Explanations

    citations and references from academic papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ori
    -0.16
    bbing
    -0.15
    aga
    -0.15
     Pend
    -0.14
     Viv
    -0.14
     Toy
    -0.14
    erdale
    -0.14
     Gauge
    -0.13
     ministry
    -0.13
     Julius
    -0.13
    POSITIVE LOGITS
    aira
    0.16
    átka
    0.15
    PHA
    0.15
    acter
    0.15
    osition
    0.14
    yk
    0.14
     slova
    0.14
     tong
    0.13
    roll
    0.13
    طر
    0.13
    Act Density 0.006%

    No Known Activations