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

    Neuronpedia

    INDEX
    Explanations

    references to social interactions involving friends

    oai_token-act-pair · gpt-3.5-turbo

    references to friends or social connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yss
    -0.72
    plet
    -0.72
     chloride
    -0.70
    grim
    -0.68
    phas
    -0.67
    umph
    -0.66
    assion
    -0.65
    ifer
    -0.64
     bearer
    -0.64
    authorized
    -0.64
    POSITIVE LOGITS
    hips
    0.96
    folk
    0.95
    liest
    0.94
    liness
    0.94
    lier
    0.92
     friends
    0.81
    channelAvailability
    0.80
    lies
    0.79
     acquaintances
    0.78
     buddies
    0.78
    Act Density 0.039%

    No Known Activations