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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interactions with other people

    oai_token-act-pair · gpt-3.5-turbo

    references to interpersonal interactions and the presence of various individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    KEY
    -0.68
    ISTORY
    -0.62
     Ecology
    -0.62
     convergence
    -0.61
     Nanto
    -0.58
    redo
    -0.58
    MN
    -0.58
    DATA
    -0.58
     mileage
    -0.58
     Manufact
    -0.57
    POSITIVE LOGITS
     whom
    0.94
     smugglers
    0.87
     inappropriately
    0.83
     behaving
    0.83
    selves
    0.82
    folk
    0.82
    soever
    0.79
     who
    0.79
     else
    0.79
     senseless
    0.77
    Act Density 0.332%

    No Known Activations