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

    Neuronpedia

    INDEX
    Explanations

    language related to self-reflection and personal feelings or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Ñģок
    -0.15
    <quote
    -0.15
    iaux
    -0.15
    boss
    -0.15
    intelligence
    -0.15
    ROLS
    -0.14
    .scalablytyped
    -0.14
    ounce
    -0.14
     FindObjectOfType
    -0.14
    462
    -0.14
    POSITIVE LOGITS
    andid
    0.17
     sac
    0.15
    -from
    0.14
    osg
    0.14
    ama
    0.14
    ion
    0.14
     shop
    0.14
     med
    0.14
    ynn
    0.14
    -widgets
    0.14
    Act Density 0.203%

    No Known Activations