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

    Neuronpedia

    INDEX
    Explanations

    statements or assertions presented as facts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     DP
    -0.36
     Comb
    -0.36
    EndContext
    -0.36
    pography
    -0.35
    postmedia
    -0.35
    жности
    -0.34
    forKey
    -0.34
    难
    -0.34
    SourceChecksum
    -0.33
     vignette
    -0.33
    POSITIVE LOGITS
     fact
    0.85
     anzi
    0.80
     indeed
    0.80
     infatti
    0.77
    indeed
    0.77
     bahkan
    0.76
    Indeed
    0.76
    事实上
    0.75
    Bahkan
    0.74
     Bahkan
    0.73
    Act Density 0.192%

    No Known Activations