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

    Neuronpedia

    INDEX
    Explanations

    like-minded individuals or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or groups with similar beliefs or values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adra
    -0.67
    atro
    -0.65
    IDS
    -0.65
    ILA
    -0.64
    avez
    -0.62
    adium
    -0.61
    ç«
    -0.61
    atin
    -0.61
    AGE
    -0.59
     morphine
    -0.59
    POSITIVE LOGITS
    edly
    1.18
    minded
    1.12
    ness
    1.06
     minded
    1.05
    llor
    0.91
    quartered
    0.90
    edIn
    0.87
    eering
    0.83
    emouth
    0.83
    iciary
    0.81
    Act Density 0.012%

    No Known Activations