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

    Neuronpedia

    INDEX
    Explanations

    events or actions related to conflict and power struggles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mắn
    -0.48
    TagMode
    -0.47
    ãy
    -0.47
     AssemblyCulture
    -0.46
     gypsy
    -0.45
     merec
    -0.45
     :,
    -0.45
    mechanical
    -0.44
     dying
    -0.43
     ();
    -0.43
    POSITIVE LOGITS
    UnusedPrivate
    0.65
     estekak
    0.65
     >=",
    0.63
    UnsafeEnabled
    0.61
    LEncoder
    0.59
     autorytatywna
    0.58
     yyr
    0.55
    RegressionTest
    0.52
     فريبيس
    0.51
     saites
    0.51
    Act Density 0.955%

    No Known Activations