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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical structures, such as buildings or biological formations

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aminer
    -0.73
    sung
    -0.68
    dan
    -0.67
    cd
    -0.67
    rr
    -0.66
    edition
    -0.66
    bat
    -0.66
    bert
    -0.65
    lymp
    -0.65
     Detective
    -0.64
    POSITIVE LOGITS
     structures
    3.64
     structure
    2.50
     Structure
    2.16
     Struct
    1.96
     constructs
    1.80
     architectures
    1.66
     buildings
    1.58
     stru
    1.54
     mechanisms
    1.51
    Struct
    1.50
    Act Density 0.015%

    No Known Activations