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

    Neuronpedia

    INDEX
    Explanations

    references to self-identity and individual autonomy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     urbanas
    -0.58
     ánh
    -0.57
    ően
    -0.57
     McIn
    -0.57
    IBOutlet
    -0.56
    覬
    -0.56
    ConfigureAwait
    -0.56
    runApp
    -0.56
    君の
    -0.55
    撿
    -0.55
    POSITIVE LOGITS
     themselves
    4.24
    themselves
    3.96
     ourselves
    3.70
     herself
    3.53
     himself
    3.50
     yourselves
    3.48
     yourself
    3.41
     Himself
    3.28
    herself
    3.23
    himself
    3.22
    Act Density 0.075%

    No Known Activations