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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iage
    -0.07
     Cah
    -0.07
    ckill
    -0.07
    ether
    -0.07
    iyas
    -0.07
    -bars
    -0.07
    bao
    -0.07
     ...)↵
    -0.06
    ume
    -0.06
    odox
    -0.06
    POSITIVE LOGITS
     And
    0.07
     unrelated
    0.06
    ET
    0.06
    amp
    0.06
     Pand
    0.05
    antis
    0.05
    ool
    0.05
     Persons
    0.05
     quot
    0.05
     pand
    0.05
    Act Density 0.012%

    No Known Activations