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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal identity and self-acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kus
    -0.14
     Minds
    -0.14
     accounts
    -0.14
     Fare
    -0.14
     priv
    -0.14
     Ost
    -0.13
    .extensions
    -0.13
     conduc
    -0.13
    EXIT
    -0.13
    >window
    -0.13
    POSITIVE LOGITS
    identity
    0.37
     identity
    0.37
     Identity
    0.35
    Identity
    0.33
    _identity
    0.32
    .identity
    0.30
     identities
    0.26
    .Identity
    0.26
     confidence
    0.23
    (identity
    0.22
    Act Density 0.284%

    No Known Activations