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

    Neuronpedia

    INDEX
    Explanations

    references to historical events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arella
    -0.18
     commod
    -0.18
    ibold
    -0.17
    mates
    -0.16
    abilia
    -0.15
     Sesso
    -0.15
    odia
    -0.15
     mate
    -0.15
     Kate
    -0.14
     Gian
    -0.14
    POSITIVE LOGITS
     Glad
    0.26
     Winston
    0.26
     Churchill
    0.25
     Prime
    0.22
    Prime
    0.21
    Church
    0.21
     Conservative
    0.21
     LORD
    0.20
     Lord
    0.20
     Lords
    0.18
    Act Density 0.058%

    No Known Activations