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

    Neuronpedia

    INDEX
    Explanations

    sequences of characters that don't form readable words or coherent patterns

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.83
    theless
    -0.80
     insult
    -0.71
     undermin
    -0.70
     Seym
    -0.69
     choked
    -0.68
     toget
    -0.68
    hens
    -0.68
     crooked
    -0.67
     accus
    -0.66
    POSITIVE LOGITS
    AppData
    1.00
    Series
    0.88
    features
    0.87
    Roaming
    0.84
    addons
    0.84
    packages
    0.83
    Parameters
    0.83
    (\
    0.82
    bryce
    0.82
    Config
    0.81
    Act Density 0.010%

    No Known Activations