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

    Neuronpedia

    INDEX
    Explanations

    terms related to recognition and praise in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oredCriteria
    -0.64
    IsMutable
    -0.57
     propOrder
    -0.56
     AssemblyCulture
    -0.54
    uxxxx
    -0.51
     EconPapers
    -0.49
    Oneof
    -0.49
    expandindo
    -0.49
     ObjectParameter
    -0.48
    nically
    -0.47
    POSITIVE LOGITS
     praise
    0.63
    praise
    0.59
     Mars
    0.48
    Dock
    0.46
     Praise
    0.45
     Dock
    0.45
    ="#"><
    0.43
    Mars
    0.43
     mars
    0.42
    comm
    0.42
    Act Density 1.651%

    No Known Activations