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

    Neuronpedia

    INDEX
    Explanations

    references to historical political events and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erin
    -0.16
    oshi
    -0.16
     Leban
    -0.16
     Rosenstein
    -0.16
     Farage
    -0.15
    ewolf
    -0.15
    .hw
    -0.15
    .protobuf
    -0.14
    Reuters
    -0.14
     Leopard
    -0.14
    POSITIVE LOGITS
     Nixon
    0.42
     Ly
    0.31
     Ronald
    0.30
     Water
    0.30
    197
    0.28
    196
    0.28
     Jimmy
    0.28
     Gerald
    0.27
     Reagan
    0.27
     Kiss
    0.27
    Act Density 0.104%

    No Known Activations