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

    Neuronpedia

    INDEX
    Explanations

    statements related to organizational missions and goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achment
    -0.17
    meal
    -0.16
    shan
    -0.15
    lish
    -0.15
    sb
    -0.14
    tlement
    -0.14
    heid
    -0.14
    asmus
    -0.14
    asan
    -0.14
    ded
    -0.13
    POSITIVE LOGITS
    erchant
    0.18
    naire
    0.16
     Welch
    0.15
    帯
    0.15
    naires
    0.15
     Gle
    0.15
    oppable
    0.14
    kyt
    0.14
    LIKELY
    0.14
    undler
    0.14
    Act Density 0.014%

    No Known Activations