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

    Neuronpedia

    INDEX
    Explanations

    elements related to programming logic and structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.46
     estekak
    -0.45
    intios
    -0.44
     SafeMath
    -0.44
    outSlope
    -0.42
     informée
    -0.40
    databind
    -0.38
    inWeight
    -0.38
    ectoria
    -0.37
    ⏜
    -0.37
    POSITIVE LOGITS
     true
    3.08
     True
    2.89
    True
    2.72
    true
    2.69
     truth
    2.56
     TRUE
    2.56
    TRUE
    2.39
    truth
    2.20
     Truth
    2.14
     verdade
    2.05
    Act Density 0.961%

    No Known Activations