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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to people or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cdecl
    -0.16
    _truth
    -0.15
    otos
    -0.14
    åĽº
    -0.14
    DataService
    -0.14
     TRI
    -0.14
    ankan
    -0.14
    quarters
    -0.14
    adelphia
    -0.14
    wh
    -0.13
    POSITIVE LOGITS
    éry
    0.15
    vert
    0.15
    ì±Ħ
    0.14
    olla
    0.14
    ymb
    0.14
    AREST
    0.14
    tabpanel
    0.14
    ç·ł
    0.14
    mast
    0.14
    vil
    0.13
    Act Density 0.069%

    No Known Activations