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

    Neuronpedia

    INDEX
    Explanations

    complex scientific terminologies and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mour
    -0.15
    arin
    -0.15
    elight
    -0.15
    ìľłë¨¸
    -0.14
    okit
    -0.14
    eci
    -0.14
    keley
    -0.13
    imedia
    -0.13
    ìŀ¡ëĭ´
    -0.13
    asje
    -0.13
    POSITIVE LOGITS
     fac
    0.16
    dna
    0.16
    anges
    0.15
     Rosenstein
    0.15
     Ka
    0.15
     Pres
    0.14
    enson
    0.14
    strup
    0.14
    ocz
    0.14
     Fal
    0.14
    Act Density 0.071%

    No Known Activations