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

    Neuronpedia

    INDEX
    Explanations

    references to political figures and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elo
    -0.16
    ellers
    -0.15
    plet
    -0.15
    %p
    -0.15
    fois
    -0.15
    Looper
    -0.14
    orent
    -0.14
    å¡ļ
    -0.14
    дина
    -0.14
    rowsers
    -0.14
    POSITIVE LOGITS
     Delaware
    0.21
     Beau
    0.21
     Biden
    0.18
     Wilmington
    0.17
    US
    0.15
     White
    0.15
     Malone
    0.14
    malar
    0.14
    202
    0.14
     mute
    0.14
    Act Density 0.032%

    No Known Activations