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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mutual interactions or agreements

    oai_token-act-pair · gpt-3.5-turbo

    concepts and instances of mutuality in relationships and agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byss
    -0.89
    mble
    -0.80
    regon
    -0.79
    mb
    -0.78
     Flags
    -0.78
    OPLE
    -0.76
    mes
    -0.72
    gun
    -0.72
    mia
    -0.71
    nox
    -0.71
    POSITIVE LOGITS
     agreement
    1.03
     acquaintance
    0.91
     mutual
    0.89
     reciproc
    0.86
     consent
    0.85
     admiration
    0.85
     acquaintances
    0.81
     parting
    0.81
     incomp
    0.79
     reciprocal
    0.78
    Act Density 0.029%

    No Known Activations