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

    Neuronpedia

    INDEX
    Explanations

    references to directory structures and file management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Monfieur
    -0.90
     Anſ
    -0.88
     transférez
    -0.87
     occaf
    -0.85
    gunas
    -0.82
     tranſ
    -0.82
     raiſ
    -0.82
    uspiel
    -0.81
     ExecuteAsync
    -0.80
     Nunn
    -0.80
    POSITIVE LOGITS
     dir
    2.02
    dir
    2.01
     Dir
    2.01
    Dir
    1.93
    DIR
    1.77
     dirs
    1.67
     directory
    1.66
    dirs
    1.65
     DIR
    1.58
    Dirs
    1.56
    Act Density 0.055%

    No Known Activations