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

    Neuronpedia

    INDEX
    Explanations

    mentions of financial figures or transactions

    oai_token-act-pair · gpt-3.5-turbo

    the character or symbol "ľ" consistently across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     manif
    -0.81
     mount
    -0.77
     incorpor
    -0.75
     psychedel
    -0.72
     slic
    -0.72
     synerg
    -0.71
     tyres
    -0.71
     electrodes
    -0.71
     stunts
    -0.70
     tides
    -0.68
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.29
    ï¸ı
    1.29
    âĶĢâĶĢ
    1.18
    âĶĢâĶĢâĶĢâĶĢ
    1.14
    âĸ¬âĸ¬
    1.06
    âĹ
    1.00
    âľ
    0.98
    âĿ
    0.91
    âĢ
    0.90
     âĢº
    0.89
    Act Density 0.104%

    No Known Activations