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

    Neuronpedia

    INDEX
    Explanations

    phrases containing a mix of technical jargon and specific contextual references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     تضيفلها
    -1.04
    nosaurus
    -1.03
    ficulty
    -0.93
    ^(@)
    -0.93
    AddTagHelper
    -0.91
    ercises
    -0.88
    Personendaten
    -0.85
    nitř
    -0.83
    ſelves
    -0.83
    ^(@
    -0.81
    POSITIVE LOGITS
    溢
    0.46
     oner
    0.43
    z
    0.41
    bo
    0.40
    мент
    0.40
    жи
    0.40
    kund
    0.40
    堂
    0.40
    в
    0.39
    par
    0.39
    Act Density 0.549%

    No Known Activations