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

    Neuronpedia

    INDEX
    Explanations

    references related to the public and its interactions with various entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the general public or public concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uana
    -0.78
    Pg
    -0.78
    kson
    -0.76
    xual
    -0.76
    atchewan
    -0.75
    imov
    -0.74
    nesota
    -0.72
    ï¸
    -0.72
    jandro
    -0.71
    veyard
    -0.71
    POSITIVE LOGITS
     relations
    0.84
     affairs
    0.81
     purse
    0.81
    izes
    0.79
     servants
    0.78
    relations
    0.77
     outcry
    0.77
     broadcaster
    0.76
    izing
    0.76
    ised
    0.75
    Act Density 0.048%

    No Known Activations