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

    Neuronpedia

    INDEX
    Explanations

    repetitive phrases or connectors in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Internal
    -0.14
     impaired
    -0.13
     Byl
    -0.13
     nackt
    -0.13
    czy
    -0.13
     uneasy
    -0.13
     abstraction
    -0.13
    oring
    -0.13
     dubious
    -0.13
    erence
    -0.13
    POSITIVE LOGITS
    iedy
    0.14
    chalk
    0.14
    ayette
    0.14
    fast
    0.14
    egal
    0.14
    vido
    0.14
    assel
    0.14
    assin
    0.14
     defe
    0.13
    çIJ
    0.13
    Act Density 0.256%

    No Known Activations