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

    Neuronpedia

    INDEX
    Explanations

    instances where a reference to a particular event or place is mentioned in relation to a topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "this."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    letes
    -0.74
    acers
    -0.73
    trump
    -0.70
    ickets
    -0.70
    rac
    -0.69
    arthed
    -0.67
    mist
    -0.67
    onis
    -0.66
     Izan
    -0.66
    winning
    -0.66
    POSITIVE LOGITS
     regard
    1.17
     vein
    1.06
     context
    1.03
     case
    0.98
     particular
    0.97
     circumstance
    0.93
     tutorial
    0.92
     manner
    0.90
     week
    0.89
     instance
    0.88
    Act Density 0.051%

    No Known Activations