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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "individual" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "independence."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    veyard
    -0.96
    Ĥİ
    -0.85
    sonian
    -0.78
    MQ
    -0.75
    calling
    -0.71
    GY
    -0.70
    zzo
    -0.69
    thora
    -0.68
    tsky
    -0.67
     Fenrir
    -0.67
    POSITIVE LOGITS
    etermin
    1.13
    ented
    1.09
    ivid
    1.01
    oled
    0.99
    irection
    0.99
    ents
    0.94
    irect
    0.92
    ocument
    0.91
    rawn
    0.90
    igo
    0.88
    Act Density 0.015%

    No Known Activations