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

    Neuronpedia

    INDEX
    Explanations

    numeric or special character sequences that are consistently repeated

    oai_token-act-pair · gpt-3.5-turbo

    special characters and formatting symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Downloadha
    -0.73
     disenfranch
    -0.71
    pton
    -0.68
     vulner
    -0.66
     Collider
    -0.65
     Fairfax
    -0.65
     merger
    -0.64
     Whats
    -0.64
     implant
    -0.63
     hemor
    -0.63
    POSITIVE LOGITS
    Ĺ
    1.14
    ŀ
    1.13
    IJ
    1.00
    ·
    0.99
    ú
    0.94
    ĺ
    0.93
    ¬
    0.89
    ļ
    0.89
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.88
    ³
    0.87
    Act Density 0.013%

    No Known Activations