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

    Neuronpedia

    INDEX
    Explanations

    references to people in managerial or leadership positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĤап
    -0.16
    erli
    -0.14
    ãģ£ãģ¨
    -0.14
    ÑĮ
    -0.14
    aign
    -0.13
    woods
    -0.13
    è¥
    -0.13
     registers
    -0.13
     bam
    -0.13
     Cah
    -0.13
    POSITIVE LOGITS
    esen
    0.17
    ader
    0.15
    elters
    0.14
    ĵn
    0.14
    uada
    0.14
    iesz
    0.14
    ekte
    0.14
    losed
    0.14
    urring
    0.14
    è«ĸ
    0.13
    Act Density 0.015%

    No Known Activations