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

    Neuronpedia

    INDEX
    Explanations

    personal names and titles related to an individual's identity and roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ⤹
    -0.41
    capai
    -0.34
     bénévol
    -0.33
     Bewußt
    -0.32
     ($)
    -0.32
     Afgan
    -0.30
    %$$
    -0.30
    RTDA
    -0.30
     skues
    -0.30
     boire
    -0.29
    POSITIVE LOGITS
     throng
    0.68
    PerformLayout
    0.61
    ForTesting
    0.60
     equally
    0.57
     okuyayım
    0.57
     troop
    0.56
     contested
    0.54
     tro
    0.53
     bagged
    0.52
     AssemblyCompany
    0.51
    Act Density 0.089%

    No Known Activations