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

    Neuronpedia

    INDEX
    Explanations

    references to high-ranking officials or positions of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ubits
    -0.16
    ibilit
    -0.16
    ög
    -0.15
    ctype
    -0.14
    jing
    -0.14
    psilon
    -0.14
    ynch
    -0.14
    ë§ģ
    -0.14
    agic
    -0.14
    orian
    -0.14
    POSITIVE LOGITS
    dom
    0.24
    lain
    0.22
     executive
    0.21
    ëª
    0.21
     Whip
    0.21
     Executive
    0.19
     Operating
    0.19
    isay
    0.19
    nut
    0.19
    -exec
    0.19
    Act Density 0.015%

    No Known Activations