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

    Neuronpedia

    INDEX
    Explanations

    directory paths and file names

    oai_token-act-pair · gpt-3.5-turbo

    file paths and directory structures in a coding or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     TAMADRA
    -0.83
     duty
    -0.81
     pronoun
    -0.75
     Era
    -0.75
     warranted
    -0.74
     possessing
    -0.73
     Him
    -0.73
     Carrie
    -0.73
     guilt
    -0.73
     Election
    -0.72
    POSITIVE LOGITS
    src
    1.53
    modules
    1.53
    include
    1.40
    python
    1.36
    bin
    1.36
    lib
    1.35
    sv
    1.34
    common
    1.34
    scripts
    1.33
    DragonMagazine
    1.33
    Act Density 0.047%

    No Known Activations