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

    Neuronpedia

    INDEX
    Explanations

    references to friends

    oai_token-act-pair · gpt-3.5-turbo

    references to friends and social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hner
    -0.68
    phas
    -0.68
    uchin
    -0.67
    oted
    -0.67
    assion
    -0.66
    ITH
    -0.65
    ifer
    -0.64
     ruling
    -0.63
    vent
    -0.63
    arcity
    -0.63
    POSITIVE LOGITS
    hips
    1.00
     friends
    0.97
     buddies
    0.95
    Friends
    0.93
     acquaintances
    0.92
    friends
    0.87
     Friends
    0.85
    folk
    0.85
     collaborators
    0.83
    hip
    0.78
    Act Density 0.029%

    No Known Activations