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

    Neuronpedia

    INDEX
    Explanations

    conversational prompts and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oga
    -0.15
    instr
    -0.14
    lah
    -0.14
    iyah
    -0.14
    antal
    -0.14
    ace
    -0.14
    angu
    -0.14
    aha
    -0.14
    ra
    -0.14
     Table
    -0.13
    POSITIVE LOGITS
     opinions
    0.30
     opinion
    0.28
     opin
    0.28
     Thoughts
    0.26
     thoughts
    0.26
     Opinion
    0.23
     comments
    0.21
     feedback
    0.20
     reactions
    0.20
    acomment
    0.20
    Act Density 0.139%

    No Known Activations