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

    Neuronpedia

    INDEX
    Explanations

    references to social criticism and commentary related to political themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _MP
    -0.16
    asing
    -0.15
    ToProps
    -0.14
    åIJ¹
    -0.14
    onas
    -0.13
    ania
    -0.13
    oÅĪ
    -0.13
     voks
    -0.13
     ydk
    -0.13
    uhn
    -0.13
    POSITIVE LOGITS
     message
    0.23
     critique
    0.23
     themes
    0.23
     sat
    0.22
     questions
    0.21
     crit
    0.21
     addressed
    0.21
     messages
    0.20
     reflection
    0.20
     Message
    0.20
    Act Density 0.349%

    No Known Activations