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

    Neuronpedia

    INDEX
    Explanations

    references to identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    InSection
    -1.08
     ***!
    -1.03
     "..\..\..\
    -0.96
    okovic
    -0.94
     "..\..\
    -0.93
     Sarac
    -0.92
    anned
    -0.92
     незавершена
    -0.91
     gouache
    -0.91
     Hawthorn
    -0.90
    POSITIVE LOGITS
     identity
    1.58
     Identity
    1.46
    Identity
    1.45
    identity
    1.27
     IDENTITY
    1.19
    IDENTITY
    1.16
     identities
    1.15
     Identities
    0.98
    identité
    0.92
     identitas
    0.85
    Act Density 0.082%

    No Known Activations