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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters and symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    milo
    -0.86
     deaf
    -0.79
     recourse
    -0.79
     mathemat
    -0.78
    rero
    -0.78
    ngth
    -0.77
     contrace
    -0.74
     tension
    -0.70
     suspensions
    -0.69
    ffen
    -0.68
    POSITIVE LOGITS
    ·
    1.35
    ´
    1.06
    į
    1.03
    ¸
    1.01
    м
    1.01
    µ
    1.01
    ر
    1.01
    ÙĨ
    1.00
    ÏĤ
    0.99
    в
    0.98
    Act Density 0.005%

    No Known Activations