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

    Neuronpedia

    INDEX
    Explanations

    folders or directories mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to folders and directory structures in computing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inge
    -0.64
     Bolton
    -0.63
     Ari
    -0.62
     Rodney
    -0.60
     Jonah
    -0.60
     Boyle
    -0.60
    aleb
    -0.60
    etheless
    -0.59
     Nash
    -0.59
     shocks
    -0.59
    POSITIVE LOGITS
     folder
    3.55
     folders
    3.11
     Folder
    2.74
    Folder
    2.45
    folder
    2.45
     directory
    2.25
     directories
    1.82
     file
    1.38
    directory
    1.37
     drawer
    1.36
    Act Density 0.021%

    No Known Activations