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

    Neuronpedia

    INDEX
    Explanations

    references to friendships and social connections between individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.71
     Houſe
    -0.67
     Anſ
    -0.66
     houſe
    -0.65
     pleaſure
    -0.65
     purpoſe
    -0.63
     uſe
    -0.61
     ſever
    -0.61
     whoſe
    -0.60
     ſeveral
    -0.59
    POSITIVE LOGITS
     friendship
    0.88
    friendship
    0.74
     amitié
    0.72
    principalColumn
    0.72
     amistad
    0.70
    Friendship
    0.70
     friendships
    0.67
     amizade
    0.64
     befri
    0.61
     cercanos
    0.61
    Act Density 0.211%

    No Known Activations