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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal relationships or interactions between individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Clever
    -0.61
     Gorge
    -0.60
    WAR
    -0.60
     Catch
    -0.56
     Fine
    -0.55
     nutshell
    -0.54
     Conversation
    -0.54
     aback
    -0.53
     Pog
    -0.53
     shaming
    -0.52
    POSITIVE LOGITS
     subsequently
    0.78
    %).
    0.76
     deemed
    0.75
     accounted
    0.74
     retained
    0.74
    ).[
    0.72
     thereafter
    0.71
    çĶ°
    0.71
    ").
    0.66
     respectively
    0.66
    Act Density 1.104%

    No Known Activations