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

    Neuronpedia

    INDEX
    Explanations

    questions and statements of identity or self-reference

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

    who and identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.47
     jScrollPane
    -0.45
    GenerationType
    -0.43
     kunjung
    -0.40
    整
    -0.40
     gator
    -0.40
    ucca
    -0.39
     gmina
    -0.38
     incomplète
    -0.37
    )=>{
    -0.37
    POSITIVE LOGITS
     Identität
    0.70
     identity
    0.68
     IDENTITY
    0.65
    是谁
    0.62
     identidade
    0.61
     identities
    0.60
    transQ
    0.60
     identité
    0.59
     identidad
    0.57
     hvem
    0.57
    Act Density 0.036%

    No Known Activations