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

    Neuronpedia

    INDEX
    Explanations

    personal pronouns and expressions of identity or emotional connection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     समीक्षक
    -0.50
     betweenstory
    -0.50
    ########.
    -0.46
    WaitGroup
    -0.45
     jsPsych
    -0.45
     considérons
    -0.43
    FontOfSize
    -0.42
    SourceChecksum
    -0.42
    gpg
    -0.41
    書館
    -0.41
    POSITIVE LOGITS
     thoughts
    0.81
     prayers
    0.81
    Thoughts
    0.80
    Sending
    0.77
     sympathies
    0.77
     Sending
    0.75
     sending
    0.72
    Prayers
    0.72
     Prayers
    0.71
     deepest
    0.70
    Act Density 0.094%

    No Known Activations