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

    Neuronpedia

    INDEX
    Explanations

    references to reliance on specific resources or materials

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate dependence or reliance on something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ACTIONS
    -0.75
     ®
    -0.74
     sidx
    -0.73
    MIT
    -0.73
    Legendary
    -0.69
    LLOW
    -0.69
    ONY
    -0.69
    estern
    -0.68
     Seen
    -0.67
    nil
    -0.65
    POSITIVE LOGITS
     propulsion
    0.98
     inspiration
    0.92
     sust
    0.86
     navigation
    0.81
     coping
    0.79
     backend
    0.79
     livelihood
    0.76
     footing
    0.75
     grounding
    0.75
     crafting
    0.74
    Act Density 0.294%

    No Known Activations