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

    Neuronpedia

    INDEX
    Explanations

    terms related to special warnings or precautions in various contexts

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

    special followed by descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مشين
    -0.62
    Clik
    -0.56
    insics
    -0.55
    haikusbot
    -0.52
    oredCriteria
    -0.52
    tamount
    -0.51
    المكان
    -0.50
    errHandler
    -0.49
    riever
    -0.49
    principalColumn
    -0.49
    POSITIVE LOGITS
     special
    1.29
    Special
    1.27
    special
    1.20
     Special
    1.13
    SPECIAL
    1.05
     SPECIAL
    1.02
     spécial
    1.00
     especiales
    0.99
     spéciale
    0.98
    特殊
    0.95
    Act Density 0.012%

    No Known Activations