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

    Neuronpedia

    INDEX
    Explanations

    key phrases and terms related to quality and assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     finally
    -0.16
    inding
    -0.15
    æĬ¤
    -0.14
    ëĿ¼ëıĦ
    -0.14
    Piece
    -0.14
    guard
    -0.14
    Protection
    -0.14
     protection
    -0.14
    ниÑĨ
    -0.14
    ä¿ĿæĬ¤
    -0.13
    POSITIVE LOGITS
     claim
    0.29
     promise
    0.28
     Claims
    0.27
     claims
    0.25
     Promise
    0.24
     Claim
    0.24
     promises
    0.24
     deal
    0.23
    promise
    0.23
    claim
    0.22
    Act Density 0.028%

    No Known Activations