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

    Neuronpedia

    INDEX
    Explanations

    words related to love and getting to know people

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to love and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    monary
    -0.74
    vu
    -0.71
    interstitial
    -0.71
    mortem
    -0.68
    route
    -0.66
    brainer
    -0.66
    nings
    -0.65
    wcs
    -0.65
    ocking
    -0.65
    quart
    -0.64
    POSITIVE LOGITS
     him
    1.11
     Him
    1.08
     them
    1.04
     oneself
    1.02
     someone
    1.01
     somebody
    0.99
     Them
    0.97
     others
    0.94
     Yourself
    0.93
     yourself
    0.92
    Act Density 0.310%

    No Known Activations