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

    Neuronpedia

    INDEX
    Explanations

    terminology related to identity within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.53
    RelativeTo
    -0.45
    oa̍t
    -0.43
     urma
    -0.43
    RegressionTest
    -0.42
    Chham
    -0.42
     DISEASE
    -0.41
     Ooster
    -0.41
    Remarque
    -0.41
    juice
    -0.40
    POSITIVE LOGITS
     identity
    2.56
     Identity
    2.30
    identity
    2.20
    Identity
    2.16
     identities
    2.03
     IDENTITY
    1.98
     identidad
    1.90
     identité
    1.87
     Identität
    1.86
     identify
    1.84
    Act Density 0.104%

    No Known Activations