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

    Neuronpedia

    INDEX
    Explanations

    mentions of activities involving family and friends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    FLICT
    -0.17
    etes
    -0.14
    angu
    -0.14
    éĻ¤
    -0.14
    irse
    -0.14
    elfare
    -0.14
     Nová
    -0.14
    iap
    -0.13
    ete
    -0.13
     chod
    -0.13
    POSITIVE LOGITS
     friends
    0.29
     family
    0.22
    friends
    0.20
     fellow
    0.19
     Friends
    0.19
    æľĭåıĭ
    0.18
     other
    0.18
     loved
    0.18
    riends
    0.18
     colleagues
    0.17
    Act Density 0.120%

    No Known Activations