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

    Neuronpedia

    INDEX
    Explanations

    phrases related to human relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases and concepts related to relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hemy
    -0.80
    sk
    -0.77
    jin
    -0.72
    fl
    -0.72
    Dou
    -0.72
    sky
    -0.71
    haps
    -0.70
    enic
    -0.70
    geon
    -0.70
    milo
    -0.69
    POSITIVE LOGITS
     relationships
    0.96
     intimately
    0.90
    ually
    0.89
     relationship
    0.89
    hips
    0.86
     partner
    0.82
     Relationship
    0.81
     between
    0.73
     intimacy
    0.73
     dynamics
    0.72
    Act Density 0.033%

    No Known Activations