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

    Neuronpedia

    INDEX
    Explanations

    folders or directories in the context of file organization

    oai_token-act-pair · gpt-3.5-turbo

    references to folders and file organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emic
    -0.77
    egal
    -0.71
    acted
    -0.70
    okin
    -0.68
    ebus
    -0.65
    acting
    -0.65
    acus
    -0.65
    acial
    -0.64
    acon
    -0.64
    ews
    -0.63
    POSITIVE LOGITS
     folder
    1.15
     folders
    1.12
     Folder
    1.12
    folder
    1.00
     drawer
    0.92
     directory
    0.80
    Folder
    0.80
    raft
    0.76
     contents
    0.76
     descriptor
    0.76
    Act Density 0.014%

    No Known Activations