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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to activities or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    references to online activity and user engagement statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udging
    -0.80
    uten
    -0.75
     deaf
    -0.75
     reconciliation
    -0.73
     eyewitness
    -0.71
     fair
    -0.70
     tongue
    -0.70
     whisk
    -0.69
    oths
    -0.69
     stricken
    -0.68
    POSITIVE LOGITS
    Activity
    1.34
     Activity
    1.08
    âĸ¬
    1.01
    ukong
    0.98
     Skydragon
    0.97
     Profile
    0.85
     Controls
    0.82
     Gems
    0.81
     Activities
    0.81
     Colo
    0.81
    Act Density 0.031%

    No Known Activations