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

    Neuronpedia

    INDEX
    Explanations

    references to significant socio-political events or government-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    owell
    -0.07
    ulan
    -0.07
    ibel
    -0.06
     Nicar
    -0.06
    atz
    -0.06
     Formal
    -0.06
    rove
    -0.06
    yan
    -0.06
    ãģ¯ãģļ
    -0.06
    åѦä¼ļ
    -0.06
    POSITIVE LOGITS
     Washington
    0.12
     London
    0.11
    Washington
    0.11
    London
    0.10
     New
    0.09
     Paris
    0.08
     Moscow
    0.08
     Washing
    0.08
     Los
    0.08
     Tokyo
    0.08
    Act Density 0.005%

    No Known Activations