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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of death

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Death" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    âĶĢâĶĢ
    -0.75
     awa
    -0.72
     diarr
    -0.70
     repentance
    -0.68
     convincing
    -0.67
     cart
    -0.66
     evid
    -0.65
     exemplary
    -0.64
    alties
    -0.64
     succession
    -0.63
    POSITIVE LOGITS
     Machine
    0.98
     Factory
    0.91
    haus
    0.89
     Fighters
    0.89
     Control
    0.88
    bringer
    0.88
     Tracker
    0.88
    Works
    0.88
     Eater
    0.87
    seek
    0.86
    Act Density 0.119%

    No Known Activations