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

    Neuronpedia

    INDEX
    Explanations

    software-related terms and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    technical components and functionalities of software systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Newark
    -0.98
     Kissinger
    -0.94
     Liberty
    -0.91
     Rhodes
    -0.89
     Morris
    -0.87
     Nelson
    -0.87
     Kerry
    -0.86
     JFK
    -0.85
     Oaks
    -0.84
     Robinson
    -0.84
    POSITIVE LOGITS
    âĢ
    2.15
    ¶
    1.55
     âĢ
    1.52
    ãĢ
    1.41
    âľ
    1.33
    âĶ
    1.31
     âĶĤ
    1.30
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.27
    â
    1.25
    ðŁij
    1.24
    Act Density 0.651%

    No Known Activations