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

    Neuronpedia

    INDEX
    Explanations

    expressions of commendation and acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dys
    -0.35
     Dys
    -0.30
     into
    -0.29
    IContainer
    -0.29
     vis
    -0.29
     _$
    -0.28
    iX
    -0.28
    `/
    -0.28
     mathvariant
    -0.27
     `/
    -0.27
    POSITIVE LOGITS
    Kudos
    1.10
     applaud
    1.01
     applauded
    1.00
     praise
    0.99
     Kudos
    0.99
     kudos
    0.98
     congratulations
    0.94
     commendable
    0.92
     Congratulations
    0.92
    congratulations
    0.92
    Act Density 0.214%

    No Known Activations