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

    Neuronpedia

    INDEX
    Explanations

    ASCII characters that are not commonly found in regular text

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     disadvant
    -0.89
     mathemat
    -0.85
     incorpor
    -0.84
     predec
    -0.82
     lawy
    -0.79
     fodder
    -0.78
     filler
    -0.76
     satell
    -0.74
     chunks
    -0.73
     synerg
    -0.72
    POSITIVE LOGITS
    ï¸ı
    1.81
     âĢº
    1.22
    âĢ
    1.19
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    1.17
    âĶĢâĶĢâĶĢâĶĢ
    1.08
    à¥
    1.05
    âĻ
    1.02
    âĶĢâĶĢ
    1.02
    女
    0.99
    âĹ
    0.98
    Act Density 0.194%

    No Known Activations