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

    Neuronpedia

    INDEX
    Explanations

    proper names or references marked by a unique symbol sequence

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to legal or political restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     dissu
    -0.69
    ertodd
    -0.69
    ionage
    -0.67
     renegoti
    -0.66
    enaries
    -0.62
    uchs
    -0.60
    vati
    -0.60
    otom
    -0.60
    venge
    -0.60
    etheless
    -0.59
    POSITIVE LOGITS
    Contents
    0.90
    Interested
    0.86
    ³³³³³³³³³³³³³³³³
    0.85
    SPONSORED
    0.83
    Guest
    0.80
    Details
    0.80
    ³³³³
    0.79
    WASHINGTON
    0.75
    Introduction
    0.73
    Published
    0.73
    Act Density 0.677%

    No Known Activations