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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "get."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    azen
    -0.18
    eworld
    -0.18
    ATEGORIES
    -0.17
    roken
    -0.17
    rellas
    -0.16
    adier
    -0.15
    exels
    -0.15
    ÏĦÏİ
    -0.15
    uzzi
    -0.15
    ihat
    -0.15
    POSITIVE LOGITS
     carried
    0.33
     worked
    0.22
     hung
    0.21
     wrapped
    0.20
     sid
    0.19
     aggravated
    0.19
     mixed
    0.19
     upset
    0.19
     carries
    0.19
     caught
    0.18
    Act Density 0.076%

    No Known Activations