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

    Neuronpedia

    INDEX
    Explanations

    conversations between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conversations or discussions

    np_acts-logits-general · gemini-2.0-flash

    conversations and telling tales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lettera
    -0.49
     public
    -0.48
    chrift
    -0.48
    rawValue
    -0.48
     publicação
    -0.48
     номина
    -0.47
    Publik
    -0.47
    glMatrixMode
    -0.46
    Writ
    -0.46
    carta
    -0.45
    POSITIVE LOGITS
     conversation
    1.15
     discussing
    0.99
     conversations
    0.97
     discussion
    0.93
     CONVERS
    0.91
     discuss
    0.91
     chatted
    0.91
     chatting
    0.90
     discussions
    0.89
     talk
    0.89
    Act Density 0.423%

    No Known Activations