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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases expressing personal growth and self-improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    loon
    -0.15
    oleon
    -0.15
    itian
    -0.14
     complexity
    -0.14
    ilated
    -0.14
    icom
    -0.14
    manı
    -0.14
    RTL
    -0.13
     shall
    -0.13
    velle
    -0.13
    POSITIVE LOGITS
     surround
    0.26
     Surround
    0.25
     surrounds
    0.20
     treat
    0.19
     surrounding
    0.19
     Treat
    0.19
     remembers
    0.18
     never
    0.16
     acknowled
    0.16
     remember
    0.16
    Act Density 0.260%

    No Known Activations