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

    Neuronpedia

    INDEX
    Explanations

    principles and concepts related to specific beliefs and values, particularly in social and community contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     دش
    -0.15
    uplic
    -0.15
    تص
    -0.15
    quelle
    -0.15
    émon
    -0.14
    _PK
    -0.14
     إد
    -0.14
    iq
    -0.13
    ullo
    -0.13
    ulle
    -0.13
    POSITIVE LOGITS
     equality
    0.24
     equal
    0.23
     mutual
    0.22
     subsidi
    0.21
     inclusion
    0.20
     consensus
    0.19
     separation
    0.19
     fair
    0.18
     univers
    0.18
     decentral
    0.18
    Act Density 0.181%

    No Known Activations