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

    Neuronpedia

    INDEX
    Explanations

    phrases related to technical development and innovation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate technological tools or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivil
    -0.72
    illin
    -0.67
    conn
    -0.65
    beat
    -0.65
    âĶ
    -0.64
    SourceFile
    -0.63
    edin
    -0.63
     externalToEVAOnly
    -0.63
    Champ
    -0.63
    lein
    -0.61
    POSITIVE LOGITS
    bidden
    1.05
    gery
    0.99
     purposes
    0.98
     beginners
    0.96
    geries
    0.94
     example
    0.91
     instance
    0.91
     starters
    0.86
    ked
    0.86
    agers
    0.81
    Act Density 0.248%

    No Known Activations