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

    Neuronpedia

    INDEX
    Explanations

    references to loved ones or familial connections

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

    loved ones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pinulongan
    -0.56
     muddy
    -0.48
     chess
    -0.47
    rzost
    -0.46
     tatuagem
    -0.44
    magitan
    -0.43
     Præ
    -0.43
     mistrzost
    -0.43
    HasIndex
    -0.43
     stupidly
    -0.42
    POSITIVE LOGITS
     Relatives
    0.64
     Lovato
    0.54
    aarrggbb
    0.54
    Folks
    0.54
    AsUp
    0.54
    elson
    0.53
     Partner
    0.53
     vänner
    0.52
     relatives
    0.52
     createDate
    0.51
    Act Density 0.003%

    No Known Activations