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

    Neuronpedia

    INDEX
    Explanations

    phrases related to geography and organizational details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yles
    -0.16
     Bobby
    -0.15
    ÏĥÏĩ
    -0.15
     Congress
    -0.14
     Hague
    -0.14
    ÏĥÏĥα
    -0.14
    ignon
    -0.14
    istrov
    -0.13
    geme
    -0.13
    anged
    -0.13
    POSITIVE LOGITS
     Mult
    0.26
    Mult
    0.25
     Raw
    0.23
    Raw
    0.22
     Abbott
    0.21
    mult
    0.20
     Bah
    0.19
    Islam
    0.19
     Gu
    0.19
     Joh
    0.19
    Act Density 0.023%

    No Known Activations