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

    Neuronpedia

    INDEX
    Explanations

    constructs related to programming functions and code execution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Good
    -0.68
     Honest
    -0.66
     Loved
    -0.63
     Easy
    -0.59
    ValueGeneration
    -0.58
     Glad
    -0.57
     Young
    -0.57
     Хоро
    -0.56
     BoxFit
    -0.56
     Sure
    -0.56
    POSITIVE LOGITS
     Parameter
    0.64
     Column
    0.61
    Parameter
    0.57
     Columns
    0.55
     Parameters
    0.55
     Segment
    0.53
     Matrix
    0.53
     Section
    0.53
     Element
    0.53
     Components
    0.51
    Act Density 0.583%

    No Known Activations