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

    Neuronpedia

    INDEX
    Explanations

    elements related to character development and interactions in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çĽĹ
    -0.15
    eny
    -0.14
    ACC
    -0.14
    butt
    -0.14
    iren
    -0.14
    ODY
    -0.14
     nghiá»ĩp
    -0.14
    éŀ
    -0.14
    ferred
    -0.13
    ardo
    -0.13
    POSITIVE LOGITS
     strength
    0.18
    strength
    0.17
     Strength
    0.16
    /inet
    0.15
    åłĤ
    0.15
     against
    0.15
     Westbrook
    0.14
     Cust
    0.14
     strengths
    0.14
    ckett
    0.14
    Act Density 0.304%

    No Known Activations