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

    Neuronpedia

    INDEX
    Explanations

    references to specific studies and their outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     civilians
    -0.50
     Mangel
    -0.47
    adra
    -0.47
     Johansen
    -0.45
     bombing
    -0.44
     Kies
    -0.44
    FontStyle
    -0.44
     Leinwand
    -0.44
    CCC
    -0.43
    ddd
    -0.43
    POSITIVE LOGITS
     CreateTagHelper
    0.56
    PathVariable
    0.56
     edges
    0.55
     outcome
    0.54
     fate
    0.52
    DockStyle
    0.47
     Outcome
    0.46
    __':
    0.46
    outcome
    0.45
     edge
    0.44
    Act Density 0.235%

    No Known Activations