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

    Neuronpedia

    INDEX
    Explanations

    conversations or discussions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "conversation" and its variations, indicating discussions or dialogues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rule
    -0.70
    fitting
    -0.70
    peria
    -0.68
    elin
    -0.67
    cheat
    -0.65
    arding
    -0.64
    feeding
    -0.61
    ADA
    -0.61
    metics
    -0.60
    iverpool
    -0.60
    POSITIVE LOGITS
     overheard
    0.97
     conversation
    0.90
    ogue
    0.87
     banter
    0.83
     conversations
    0.81
     about
    0.77
     starter
    0.77
    osphere
    0.74
     Conversation
    0.74
     discussing
    0.73
    Act Density 0.069%

    No Known Activations