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

    Neuronpedia

    INDEX
    Explanations

    transitional phrases and structural elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upe
    -0.16
    509
    -0.15
    SystemService
    -0.15
    pedia
    -0.14
    ellular
    -0.14
    cripts
    -0.14
    ÙĬØ©
    -0.14
    erus
    -0.14
    ena
    -0.14
    äll
    -0.14
    POSITIVE LOGITS
    hack
    0.16
     Hack
    0.15
    Hack
    0.14
    EEP
    0.14
     hack
    0.14
    zug
    0.14
     Bain
    0.14
    è¼
    0.14
    deo
    0.14
    hort
    0.13
    Act Density 0.001%

    No Known Activations