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

    Neuronpedia

    INDEX
    Explanations

    names of individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    è¦ļéĨĴ
    -0.82
    igham
    -0.79
    ittal
    -0.79
    daq
    -0.73
    ulic
    -0.73
     livest
    -0.72
    itism
    -0.70
    essage
    -0.70
     Corvette
    -0.70
     Proced
    -0.70
    POSITIVE LOGITS
    arte
    1.01
     Shu
    0.91
    Ku
    0.82
    FO
    0.81
    XY
    0.80
    ãĤ«
    0.80
     Uri
    0.79
    olkien
    0.78
    KEN
    0.75
    ARGET
    0.74
    Act Density 0.029%

    No Known Activations