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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their actions or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    práv
    -0.64
    ImageContext
    -0.63
    RuleContext
    -0.52
    lossene
    -0.52
    diyesi
    -0.52
    javax
    -0.50
    kreises
    -0.49
    良
    -0.49
    eaways
    -0.49
    декса
    -0.48
    POSITIVE LOGITS
     formerly
    0.73
     vốn
    0.67
     übrigens
    0.67
     famously
    0.64
    Vidite
    0.63
    AutoField
    0.61
     renamed
    0.61
     whoſe
    0.61
    __':
    0.60
     EnglishChoose
    0.59
    Act Density 0.202%

    No Known Activations