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

    Neuronpedia

    INDEX
    Explanations

    references to political power structures and ruling entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ules
    -0.15
     Stick
    -0.14
    ç¯
    -0.14
     Flip
    -0.14
    наÑĩе
    -0.14
    Stick
    -0.14
     IDictionary
    -0.13
    Flip
    -0.13
    esium
    -0.13
    tick
    -0.13
    POSITIVE LOGITS
    AndView
    0.18
    arnation
    0.15
    erten
    0.14
    á»ı
    0.14
    AndGet
    0.14
    uter
    0.14
     Wich
    0.13
    -party
    0.13
    iram
    0.13
    geber
    0.13
    Act Density 0.010%

    No Known Activations