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

    Neuronpedia

    INDEX
    Explanations

    references to "you" in various contexts, indicating a focus on direct address and personal connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ær
    -0.18
    htag
    -0.15
    ghest
    -0.15
    akat
    -0.14
    cors
    -0.14
    .Tick
    -0.14
    oyal
    -0.13
    edb
    -0.13
     testify
    -0.13
    Assembly
    -0.13
    POSITIVE LOGITS
     can
    0.19
     Gran
    0.16
    can
    0.15
     sees
    0.15
     cannot
    0.15
     See
    0.15
    cheng
    0.15
     see
    0.15
    nger
    0.15
     element
    0.14
    Act Density 0.209%

    No Known Activations