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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and invitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aft
    -0.15
    uat
    -0.15
     Feel
    -0.14
    каÑģ
    -0.14
    âķIJ
    -0.14
     Nga
    -0.14
    aye
    -0.14
    ession
    -0.13
    cdf
    -0.13
    elling
    -0.13
    POSITIVE LOGITS
     extend
    0.29
     extends
    0.25
    extend
    0.24
     express
    0.24
     extended
    0.23
     wish
    0.23
     extent
    0.23
     Wish
    0.22
     say
    0.20
     convey
    0.20
    Act Density 0.041%

    No Known Activations