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

    Neuronpedia

    INDEX
    Explanations

    positive adjectives describing people or their traits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     librarian
    -0.16
    ritos
    -0.15
    anes
    -0.15
    kou
    -0.15
    upp
    -0.15
     Coding
    -0.15
    anon
    -0.14
    é«ĺæ¸ħ
    -0.14
    çī
    -0.14
    endar
    -0.14
    POSITIVE LOGITS
     deleg
    0.21
     communic
    0.18
     dresser
    0.18
     convers
    0.18
     negot
    0.18
     addition
    0.18
     Communic
    0.17
    Presence
    0.17
     comunic
    0.17
     storyt
    0.16
    Act Density 0.106%

    No Known Activations