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

    Neuronpedia

    INDEX
    Explanations

    references to various research centers and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fle
    -0.18
    ensa
    -0.18
     Fle
    -0.18
    olly
    -0.15
    ering
    -0.14
    ager
    -0.14
     Wen
    -0.14
    eration
    -0.13
    Wik
    -0.13
    yat
    -0.13
    POSITIVE LOGITS
     Excellence
    0.24
     excellence
    0.21
     Excell
    0.17
     Advanced
    0.17
     excell
    0.17
     gravity
    0.17
     Adv
    0.16
     Applied
    0.16
    annon
    0.15
     Gravity
    0.15
    Act Density 0.034%

    No Known Activations