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

    Neuronpedia

    INDEX
    Explanations

    names of people, especially focusing on the name "Nina" and similar variations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific names, particularly associated with notable individuals and possible issues related to overdoses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    auga
    -0.86
    poral
    -0.85
    stall
    -0.83
    ership
    -0.83
    rior
    -0.82
    lain
    -0.81
    respond
    -0.81
    ATIONAL
    -0.78
    hip
    -0.77
    ary
    -0.74
    POSITIVE LOGITS
    cats
    0.77
     Von
    0.73
    Els
    0.68
     Ludwig
    0.68
     Tycoon
    0.66
     Dob
    0.65
    cat
    0.65
    Dust
    0.64
     Mae
    0.63
    Elsa
    0.62
    Act Density 0.039%

    No Known Activations