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

    Neuronpedia

    INDEX
    Explanations

    instances of invitations or requests involving the word "to"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rag
    -0.81
    borne
    -0.70
    worn
    -0.70
    enforcement
    -0.67
    Pg
    -0.66
    ray
    -0.64
    entimes
    -0.64
    gradient
    -0.64
     indicators
    -0.63
    pointer
    -0.63
    POSITIVE LOGITS
     participate
    1.12
     join
    1.11
     dinner
    0.98
     partake
    0.94
     meet
    0.91
     explore
    0.90
     celebrate
    0.90
     testify
    0.86
     congratulate
    0.86
     nominate
    0.85
    Act Density 0.049%

    No Known Activations