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

    Neuronpedia

    INDEX
    Explanations

    phrases related to diplomatic relations and political statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï
    -0.18
    ladu
    -0.17
    å
    -0.15
    овоÑĢ
    -0.15
    ël
    -0.15
    ético
    -0.14
     Incontri
    -0.14
     Cheat
    -0.14
    erd
    -0.14
    gnore
    -0.14
    POSITIVE LOGITS
     Brno
    0.21
     âĢŀ
    0.21
     Velvet
    0.19
     Slovak
    0.19
     Boh
    0.19
     Czech
    0.19
     cca
    0.18
     PlzeÅĪ
    0.17
    TOP
    0.16
    âĢŀ
    0.16
    Act Density 0.050%

    No Known Activations