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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the need for identification or documentation

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to identification requirements and voting regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.84
    storms
    -0.82
    âĶĢâĶĢâĶĢâĶĢ
    -0.81
    ~~~~~~~~
    -0.75
     rebound
    -0.72
    frey
    -0.71
    ovie
    -0.71
    fell
    -0.68
    warm
    -0.68
    adj
    -0.68
    POSITIVE LOGITS
     passports
    1.87
     passport
    1.70
     IDs
    1.55
     fingerprint
    1.49
     identification
    1.47
     fingerprints
    1.42
     citizenship
    1.34
     Visa
    1.34
     authentication
    1.30
     ID
    1.28
    Act Density 0.885%

    No Known Activations