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

    Neuronpedia

    INDEX
    Explanations

    locations or settings where people interact socially, possibly leading to conflicts

    oai_token-act-pair · gpt-3.5-turbo

    scenarios involving social interactions and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elin
    -0.83
    ilty
    -0.74
    ector
    -0.72
    eele
    -0.71
    ected
    -0.65
     Pwr
    -0.64
     Assets
    -0.64
    atts
    -0.64
    assets
    -0.63
    attribute
    -0.63
    POSITIVE LOGITS
     conversation
    1.66
     discussion
    1.57
     discussions
    1.52
     banter
    1.47
     conversations
    1.45
     Conversation
    1.42
     disagreement
    1.38
     debate
    1.37
    Discussion
    1.34
     dialogue
    1.33
    Act Density 0.916%

    No Known Activations