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

    Neuronpedia

    INDEX
    Explanations

    code structure and elements related to programming templates and object identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Creates
    -0.88
     Finds
    -0.87
     Draws
    -0.86
    Draws
    -0.84
    Starts
    -0.82
     Builds
    -0.81
    Takes
    -0.80
    Makes
    -0.79
    Builds
    -0.78
    Runs
    -0.78
    POSITIVE LOGITS
     settle
    0.68
     marry
    0.65
     kill
    0.64
     restore
    0.61
     protect
    0.61
     teach
    0.60
     earn
    0.60
     serve
    0.58
     motivate
    0.58
     finish
    0.58
    Act Density 0.343%

    No Known Activations