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

    Neuronpedia

    INDEX
    Explanations

    elements related to treaties and agreements involving leaders and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tips
    -0.16
     Hoy
    -0.15
    á»ĩn
    -0.15
     Glas
    -0.14
    elta
    -0.14
     Banks
    -0.14
     Tips
    -0.14
     workers
    -0.14
     PS
    -0.14
     bombs
    -0.14
    POSITIVE LOGITS
     sober
    0.21
     rein
    0.19
     govern
    0.17
     go
    0.17
     envi
    0.17
     feud
    0.16
    Alias
    0.15
     usur
    0.15
     siti
    0.15
     ali
    0.15
    Act Density 0.025%

    No Known Activations