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

    Neuronpedia

    INDEX
    Explanations

    instances of dependency on specific resources or conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating reliance or dependence on something or someone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Collider
    -0.77
     Derby
    -0.76
    Pen
    -0.71
     Lange
    -0.68
    76561
    -0.67
     Shades
    -0.67
     Indigo
    -0.67
     Edited
    -0.66
     sidx
    -0.65
    ubuntu
    -0.64
    POSITIVE LOGITS
     sust
    1.05
     livelihood
    1.04
     survival
    0.95
     help
    0.89
     salvation
    0.84
     nour
    0.83
     upkeep
    0.82
     stabil
    0.82
     coping
    0.81
     stabilize
    0.77
    Act Density 0.308%

    No Known Activations