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

    Neuronpedia

    INDEX
    Explanations

    references to family relationships and significant others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    family relationships and personal anecdotes

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    vernment
    -0.76
    pire
    -0.66
    arnaev
    -0.66
     themselves
    -0.64
    unin
    -0.63
    ensus
    -0.62
    utterstock
    -0.61
    ettlement
    -0.61
    ensions
    -0.61
     guiName
    -0.60
    POSITIVE LOGITS
     loves
    0.95
    my
    0.89
     hates
    0.88
     todd
    0.81
     didnt
    0.79
     my
    0.79
     texted
    0.77
     likes
    0.77
     bought
    0.76
     prefers
    0.75
    Act Density 0.150%

    No Known Activations