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

    Neuronpedia

    INDEX
    Explanations

    expressions of gratitude and appreciation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    imat
    -0.18
    etÃŃ
    -0.15
    omit
    -0.15
    tero
    -0.15
    /generated
    -0.14
    757
    -0.14
     åħ
    -0.14
    mint
    -0.14
     Geg
    -0.14
    vÄĽt
    -0.14
    POSITIVE LOGITS
     interact
    0.34
     interaction
    0.32
     interacts
    0.31
    interaction
    0.30
     Interaction
    0.29
     interactions
    0.27
    Interaction
    0.26
     meet
    0.26
     interacting
    0.25
     meeting
    0.25
    Act Density 0.285%

    No Known Activations