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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical concepts and structures in formal logic and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gaard
    -0.15
    çĮ
    -0.14
    ldr
    -0.14
    MLS
    -0.14
    _rsp
    -0.14
    .COL
    -0.14
    anim
    -0.14
     à¤Ńà¤Ĺ
    -0.13
    é¼
    -0.13
    nga
    -0.13
    POSITIVE LOGITS
     Alice
    0.34
    Alice
    0.28
     Bell
    0.28
     Bob
    0.28
     ent
    0.26
     alice
    0.25
     quantum
    0.25
     Eve
    0.24
    Bob
    0.24
    alice
    0.24
    Act Density 0.006%

    No Known Activations