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

    Neuronpedia

    INDEX
    Explanations

    words related to interpersonal relationships

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hemy
    -0.87
    milo
    -0.80
    sk
    -0.76
    Dou
    -0.71
    sky
    -0.70
    rpm
    -0.69
    gow
    -0.69
    geon
    -0.69
    prus
    -0.68
    jin
    -0.67
    POSITIVE LOGITS
     relationships
    0.94
     relationship
    0.92
    ually
    0.87
     intimately
    0.86
    hips
    0.82
     partner
    0.82
     between
    0.81
     Relationship
    0.80
     relations
    0.76
     dynamics
    0.74
    Act Density 0.038%

    No Known Activations