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

    Neuronpedia

    INDEX
    Explanations

    file paths in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    file paths and directory structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Beir
    -0.92
    terday
    -0.82
    glers
    -0.80
     Briggs
    -0.72
     pneum
    -0.72
     Faw
    -0.71
     leaps
    -0.69
     Bentley
    -0.67
     swat
    -0.66
     Faul
    -0.65
    POSITIVE LOGITS
    usr
    1.35
    home
    1.18
    ËĪ
    1.14
    tmp
    1.12
    etc
    1.11
    Applications
    1.05
    Users
    1.03
    opt
    1.03
    wcsstore
    1.02
    proc
    0.98
    Act Density 0.019%

    No Known Activations