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

    Neuronpedia

    INDEX
    Explanations

    mentions of something being present, or happening in a particular place

    oai_token-act-pair · gpt-3.5-turbo

    instances of people and entities described as being present or active in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaries
    -0.86
    aughs
    -0.78
    ospels
    -0.70
     brill
    -0.66
    earchers
    -0.63
    irth
    -0.61
     Rhodes
    -0.59
     Honour
    -0.59
    asty
    -0.58
    ggles
    -0.58
    POSITIVE LOGITS
    âĢ
    1.65
     âĢ
    1.29
    .�
    1.07
    âĢł
    1.06
    âĿ
    1.01
    âĺ
    0.96
    §
    0.96
    âĸ
    0.96
    âľ
    0.95
    """
    0.94
    Act Density 0.613%

    No Known Activations