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

    Neuronpedia

    INDEX
    Explanations

    pronouns and expressions indicating self-reference or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    seamnă
    -0.62
     kasarigan
    -0.59
    htë
    -0.50
    îné
    -0.46
     kimi
    -0.46
     belki
    -0.46
    mogat
    -0.45
    Incoming
    -0.45
     doros
    -0.43
     Incoming
    -0.42
    POSITIVE LOGITS
    ')],
    0.80
     protoimpl
    0.76
    tagHelperRunner
    0.75
    }")
    0.75
     ddelweddau
    0.73
    "))
    0.72
     BorderRadius
    0.72
    '))
    0.72
    ')}
    0.72
    """)
    0.72
    Act Density 0.133%

    No Known Activations