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

    Neuronpedia

    INDEX
    Explanations

    expressions of social relationships and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    featureID
    -0.93
    تقاوى
    -0.82
    ValueStyle
    -0.76
    Lähteet
    -0.74
     >=",
    -0.72
    XmlAccessType
    -0.71
     autorytatywna
    -0.70
     kasarigan
    -0.69
    enderror
    -0.68
    VersionUID
    -0.67
    POSITIVE LOGITS
     friendship
    0.97
     amistad
    0.85
     Friendship
    0.83
     friendships
    0.80
     befri
    0.80
    Friendship
    0.77
     amizade
    0.77
     interact
    0.74
    friendship
    0.73
     interacting
    0.72
    Act Density 0.255%

    No Known Activations