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

    Neuronpedia

    INDEX
    Explanations

    computer code related to file operations and debugging

    oai_token-act-pair · gpt-3.5-turbo

    computer file types and coding-related terms or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     critically
    -0.62
     positively
    -0.62
     Pes
    -0.62
     incredibly
    -0.60
     historically
    -0.58
     empowering
    -0.58
     limb
    -0.57
     Ambrose
    -0.57
     Schne
    -0.57
     Ninth
    -0.57
    POSITIVE LOGITS
    tenance
    1.17
    info
    1.17
    _
    1.13
    dir
    1.00
    __
    0.99
    name
    0.98
    widget
    0.98
    ername
    0.98
    menu
    0.96
    drop
    0.95
    Act Density 0.187%

    No Known Activations