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

    Neuronpedia

    INDEX
    Explanations

    expressions related to social etiquette and behavior

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

    acceptance and observation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     battre
    -0.40
    contentLoaded
    -0.40
    BlockingQueue
    -0.38
     Amplitude
    -0.37
     Lest
    -0.37
     batte
    -0.37
     Mission
    -0.36
    blum
    -0.36
     patterning
    -0.36
    SBATCH
    -0.36
    POSITIVE LOGITS
     Мексичка
    0.46
     ddelweddau
    0.43
     frown
    0.43
    Зноскі
    0.43
     Exactos
    0.42
    GTCX
    0.42
     <<<<<<<<<<<<<<
    0.41
    ArrowToggle
    0.41
     Erwartungen
    0.40
     frowned
    0.40
    Act Density 0.099%

    No Known Activations