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

    Neuronpedia

    INDEX
    Explanations

    demonstrative pronouns in various languages

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

    demonstrative pronouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.68
    adl
    -0.54
    FieldNumber
    -0.54
     Liban
    -0.51
    msgTypes
    -0.51
     feroit
    -0.50
    MRP
    -0.49
    탉
    -0.49
    ADM
    -0.48
    ADL
    -0.47
    POSITIVE LOGITS
     this
    0.96
     questa
    0.91
    This
    0.91
     THIS
    0.90
     dieser
    0.88
    Этот
    0.88
     This
    0.85
     cette
    0.84
     Этот
    0.82
     denna
    0.82
    Act Density 0.003%

    No Known Activations