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

    Neuronpedia

    INDEX
    Explanations

    references to conversations and exchanges between individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onen
    -0.18
    ÏĢοÏį
    -0.14
    mention
    -0.14
     Dess
    -0.14
    ToSend
    -0.14
    dess
    -0.14
    919
    -0.14
    entai
    -0.14
    agit
    -0.13
    shint
    -0.13
    POSITIVE LOGITS
     conversation
    0.41
     conversations
    0.36
     dialogue
    0.35
     exchanges
    0.35
    conversation
    0.34
     Conversation
    0.32
     exchange
    0.32
    Conversation
    0.31
     dialog
    0.29
     Convers
    0.28
    Act Density 0.224%

    No Known Activations