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

    Neuronpedia

    INDEX
    Explanations

    phrases related to individuality and uniqueness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize autonomy and individual rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cussion
    -0.70
    ashtra
    -0.69
    amba
    -0.67
    cery
    -0.67
    cott
    -0.66
    uve
    -0.66
    jug
    -0.66
    ulic
    -0.65
    aundering
    -0.64
    unction
    -0.64
    POSITIVE LOGITS
     selves
    0.79
    imei
    0.63
     counterparts
    0.63
     creations
    0.62
    iHUD
    0.60
     pursuits
    0.59
    iations
    0.59
    blance
    0.59
     chromosome
    0.58
     Rossi
    0.58
    Act Density 0.150%

    No Known Activations