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

    Neuronpedia

    INDEX
    Explanations

    words related to effort or energy

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "effort" and its derivatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SpaceEngineers
    -0.80
     guiActiveUnfocused
    -0.78
     helicopters
    -0.77
    SHIP
    -0.74
     antidepressants
    -0.72
    ãĥ¯ãĥ³
    -0.71
    kees
    -0.71
    REDACTED
    -0.71
     Ou
    -0.68
    xual
    -0.66
    POSITIVE LOGITS
    endi
    1.25
    iency
    1.08
    luent
    1.07
    encing
    1.00
    rites
    0.96
    emin
    0.96
    usive
    0.90
    iencies
    0.90
    itt
    0.90
    sburg
    0.90
    Act Density 0.011%

    No Known Activations