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

    Neuronpedia

    INDEX
    Explanations

    references to companionship or social connections

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

    "with" followed by a family/friend related word

    np_acts-logits-general · gemini-2.0-flash

    social relationships with people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     houſe
    -0.56
    ſelf
    -0.52
     ſever
    -0.50
     themſelves
    -0.50
    orini
    -0.48
    vidia
    -0.48
    Créditos
    -0.48
     ſch
    -0.46
     pleaſure
    -0.46
     leaſt
    -0.46
    POSITIVE LOGITS
     friends
    1.25
     buddies
    1.06
     pals
    1.04
     fellow
    1.04
    friends
    1.04
     friend
    1.02
     colleagues
    0.97
     companions
    0.95
     φί
    0.93
    friend
    0.90
    Act Density 0.171%

    No Known Activations