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

    Neuronpedia

    INDEX
    Explanations

    terms related to dialects and psychiatric conditions

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

    linguistic and psychiatric terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HSC
    -0.48
    永
    -0.48
     HSC
    -0.46
    MMS
    -0.42
    ”:
    -0.41
    ∼
    -0.39
    Nicolas
    -0.39
     Winona
    -0.38
    Jonas
    -0.38
     Marcos
    -0.38
    POSITIVE LOGITS
    pert
    1.00
    dialect
    0.98
     dialect
    0.90
     pert
    0.90
     PERT
    0.88
    Pert
    0.87
     Pert
    0.86
     للمعارف
    0.84
    Dialect
    0.83
    PERT
    0.82
    Act Density 0.016%

    No Known Activations