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

    Neuronpedia

    INDEX
    Explanations

    words associated with power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .scalablytyped
    -0.17
    lify
    -0.16
    æ½
    -0.15
    ulse
    -0.15
    uspend
    -0.15
    rief
    -0.15
    ovation
    -0.15
    ìĭľìĺ¤
    -0.15
    notif
    -0.15
    صÙģ
    -0.15
    POSITIVE LOGITS
    еÑģа
    0.16
    tra
    0.16
     Garner
    0.14
     h
    0.14
     "
    0.14
    ome
    0.14
    chem
    0.14
     duty
    0.14
     mim
    0.13
    upp
    0.13
    Act Density 0.011%

    No Known Activations