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

    Neuronpedia

    INDEX
    Explanations

    references to positions of authority and leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŀæĢ§
    -0.15
    Swift
    -0.15
    swift
    -0.14
    assa
    -0.14
     ÎĶε
    -0.13
    unce
    -0.13
    ÅĽnie
    -0.13
     carr
    -0.13
    urer
    -0.13
    115
    -0.13
    POSITIVE LOGITS
    azer
    0.16
    ookie
    0.15
     Beth
    0.14
     ex
    0.14
    lef
    0.14
     John
    0.13
     Grant
    0.13
     metam
    0.13
    ẩm
    0.13
    Ùĥس
    0.13
    Act Density 0.337%

    No Known Activations