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

    Neuronpedia

    INDEX
    Explanations

    words related to mutual relationships and agreements

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to mutual relationships and cooperation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    regon
    -0.83
    byss
    -0.80
    dq
    -0.76
    ixel
    -0.73
    agate
    -0.70
    kins
    -0.70
    den
    -0.70
    mob
    -0.69
     Dare
    -0.69
     Flags
    -0.68
    POSITIVE LOGITS
     agreement
    0.92
     mutual
    0.92
     acquaintance
    0.88
     reciproc
    0.86
     admiration
    0.83
     parting
    0.80
     acquaintances
    0.79
     masturbation
    0.78
     incomp
    0.78
     correspondence
    0.76
    Act Density 0.025%

    No Known Activations