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

    Neuronpedia

    INDEX
    Explanations

    questions and requests for assistance or advice

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

    asking how I can or should do

    np_acts-logits-general · gemini-2.5-flash-lite

    Questions asking for advice or instructions framed from the speaker's perspective (tokens like "I", "should", "do", "how should I", "what should I do").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    TagMode
    -0.49
    ScopeManager
    -0.41
    Diweddarwch
    -0.39
     peccato
    -0.34
    MetaType
    -0.33
     ffilmiau
    -0.32
     affinity
    -0.30
    Décès
    -0.30
     met
    -0.30
     saluto
    -0.30
    POSITIVE LOGITS
     Administrativna
    0.66
     purpoſe
    0.56
    vician
    0.52
     Савезне
    0.48
    rungsseite
    0.47
     Inscrivez
    0.46
    WriteBarrier
    0.46
    querque
    0.46
    OCCURRED
    0.46
     occaf
    0.45
    Act Density 0.072%

    No Known Activations