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

    Neuronpedia

    INDEX
    Explanations

    narratives or excerpts related to personal relationships and emotional experiences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     themselves
    -0.72
    idates
    -0.60
    aic
    -0.60
     Trident
    -0.58
     convened
    -0.58
     Lic
    -0.57
    EMS
    -0.57
     Networks
    -0.57
     Hole
    -0.56
     Highlands
    -0.56
    POSITIVE LOGITS
     myself
    1.17
     personally
    0.77
    oan
    0.76
    poke
    0.69
     my
    0.69
     writing
    0.68
    cffff
    0.67
     thankful
    0.67
    ebin
    0.66
     gonna
    0.66
    Act Density 14.494%

    No Known Activations