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

    Neuronpedia

    INDEX
    Explanations

    references to support and opposition in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rana
    -0.15
    ebek
    -0.14
    ild
    -0.14
    tas
    -0.14
    iÄĻ
    -0.14
    ůr
    -0.14
     reife
    -0.14
     Chan
    -0.13
    egan
    -0.13
    affe
    -0.13
    POSITIVE LOGITS
     notion
    0.19
     against
    0.17
    /support
    0.16
     idea
    0.16
     notions
    0.15
     Tod
    0.15
    Ùģت
    0.15
     crypt
    0.15
     bele
    0.15
    ston
    0.14
    Act Density 0.131%

    No Known Activations