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

    Neuronpedia

    INDEX
    Explanations

    events related to personal and emotional relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     my
    -0.67
     mijn
    -0.64
     meines
    -0.60
     saya
    -0.58
     mojej
    -0.58
     Wicidata
    -0.56
     moim
    -0.54
     meiner
    -0.51
     moje
    -0.50
     моя
    -0.49
    POSITIVE LOGITS
     flashback
    0.87
     blackmail
    0.86
     overheard
    0.84
     reveals
    0.80
     confesses
    0.78
     flashbacks
    0.77
     revealed
    0.77
    revealed
    0.76
     alibi
    0.75
     Elsewhere
    0.74
    Act Density 0.389%

    No Known Activations