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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical exercises and workout activities

    oai_token-act-pair · gpt-3.5-turbo

    references to workouts and exercise routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alty
    -0.80
     presiding
    -0.69
    utter
    -0.68
    grave
    -0.68
    gently
    -0.68
    alties
    -0.66
     tongues
    -0.65
    responsible
    -0.65
    recy
    -0.64
    por
    -0.63
    POSITIVE LOGITS
     workout
    1.12
     workouts
    1.08
     regimen
    0.91
     Trainer
    0.81
    è¦ļéĨĴ
    0.76
    mens
    0.76
     routines
    0.75
    halla
    0.75
     Skydragon
    0.74
     trainer
    0.72
    Act Density 0.005%

    No Known Activations