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

    Neuronpedia

    INDEX
    Explanations

    references to physical fitness activities and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to fitness and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    akedown
    -0.82
    ectar
    -0.76
    ãĥĥãĥī
    -0.73
     Rockefeller
    -0.70
    enic
    -0.65
     Helpful
    -0.64
     Roses
    -0.63
    âĸ¬
    -0.62
     Roof
    -0.61
    prop
    -0.61
    POSITIVE LOGITS
     fitness
    0.95
     regimen
    0.90
     Trainer
    0.87
     trainer
    0.84
     credentials
    0.82
    ternity
    0.82
     trainers
    0.81
     Fighters
    0.79
    ability
    0.78
     Fitness
    0.78
    Act Density 0.018%

    No Known Activations