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

    Neuronpedia

    INDEX
    Explanations

    verbs related to achievements or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to achievement or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     includ
    -0.78
    gas
    -0.76
    rats
    -0.70
    rians
    -0.65
    ator
    -0.65
     ling
    -0.64
    otics
    -0.63
     injected
    -0.63
    bringing
    -0.63
    obe
    -0.61
    POSITIVE LOGITS
     Waterloo
    0.98
     Worlds
    0.88
     relegation
    0.87
     orbit
    0.84
     Wembley
    0.83
     Daytona
    0.80
     bankruptcy
    0.80
     PAX
    0.80
     Everest
    0.78
     Valhalla
    0.78
    Act Density 0.248%

    No Known Activations