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

    Neuronpedia

    INDEX
    Explanations

    concepts related to identity, especially in the context of personal, ethnic, or cultural identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uter
    -0.16
    mouth
    -0.16
    ese
    -0.15
     CALLBACK
    -0.15
     mouths
    -0.14
    identified
    -0.14
    ãĥ©ãĥĥãĤ¯
    -0.14
    stood
    -0.14
    ilos
    -0.14
    aze
    -0.13
    POSITIVE LOGITS
     theft
    0.34
     Theft
    0.31
     crisis
    0.30
     Crisis
    0.30
     crises
    0.26
     politics
    0.26
     formation
    0.25
    ENTITY
    0.25
     cards
    0.24
     card
    0.24
    Act Density 0.035%

    No Known Activations