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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional connections and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rins
    -0.14
     travers
    -0.14
    ãĤĮãģ©
    -0.13
     adher
    -0.13
     waren
    -0.13
    ãģĹãģ¦ãĤĭ
    -0.13
     ÙĩستÙĨد
    -0.13
    oplast
    -0.12
    fty
    -0.12
    nga
    -0.12
    POSITIVE LOGITS
     get
    0.35
     take
    0.35
     perform
    0.33
     receive
    0.33
     find
    0.32
     undertake
    0.32
     pursue
    0.31
     explore
    0.31
     start
    0.31
     engage
    0.31
    Act Density 3.300%

    No Known Activations