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

    Neuronpedia

    INDEX
    Explanations

    instances of formal language and narratives, particularly around authority and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    starting a new clause or sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    الحياه
    -0.69
    ſelves
    -0.64
    ftagPool
    -0.64
    Personendaten
    -0.64
     myſelf
    -0.63
     ſta
    -0.61
     témoig
    -0.61
     $_(
    -0.59
    WriteBarrier
    -0.59
     pleaſure
    -0.57
    POSITIVE LOGITS
    ...
    0.35
     createState
    0.35
     complacency
    0.34
    No
    0.33
     чего
    0.30
     Mitter
    0.30
    Not
    0.29
    o
    0.29
     doInBackground
    0.29
     ве
    0.29
    Act Density 0.028%

    No Known Activations