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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a successful or popular outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .AI
    -0.15
    phalt
    -0.15
    ulti
    -0.15
    _roi
    -0.14
    ık
    -0.14
    riott
    -0.14
    ultan
    -0.14
    ">ÃĹ</
    -0.13
    rica
    -0.13
     report
    -0.13
    POSITIVE LOGITS
    reff
    0.17
    WR
    0.16
     Ding
    0.15
    NECT
    0.14
    ands
    0.14
     itemprop
    0.14
    strar
    0.14
     VX
    0.13
    theses
    0.13
    iffies
    0.13
    Act Density 0.011%

    No Known Activations