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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political leadership and decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ----</
    -0.18
    ubat
    -0.16
    ovÃŃ
    -0.15
    ÃĸL
    -0.15
    TAIL
    -0.14
    é±
    -0.14
    iasi
    -0.14
    geh
    -0.14
    HEET
    -0.14
    ensor
    -0.13
    POSITIVE LOGITS
     himself
    0.26
     personally
    0.22
     personal
    0.20
     his
    0.19
     Himself
    0.17
    personal
    0.17
     Personally
    0.16
     Personal
    0.16
    his
    0.15
    ajan
    0.15
    Act Density 0.429%

    No Known Activations