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

    Neuronpedia

    INDEX
    Explanations

    concepts related to foundational principles and frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ«ãĥķ
    -0.17
    mana
    -0.17
    ç¯
    -0.16
    antino
    -0.15
    .appspot
    -0.15
    адÑĥ
    -0.14
    Ïīνα
    -0.14
    ood
    -0.14
     pylint
    -0.14
    _shapes
    -0.14
    POSITIVE LOGITS
     principles
    0.19
     principle
    0.17
     premises
    0.17
     Principles
    0.16
     principals
    0.15
    795
    0.15
     premise
    0.15
     based
    0.15
    657
    0.14
    based
    0.14
    Act Density 0.090%

    No Known Activations