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

    Neuronpedia

    INDEX
    Explanations

    **world-related** terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'world.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippi
    -0.96
    veyard
    -0.93
    EStream
    -0.86
    WARE
    -0.83
    ibility
    -0.79
    edin
    -0.78
    shapeshifter
    -0.77
    irez
    -0.77
    ients
    -0.74
    Acknowled
    -0.74
    POSITIVE LOGITS
    wide
    0.92
     renown
    0.85
     premiere
    0.82
     wide
    0.82
     domination
    0.79
     heavyweight
    0.77
     religions
    0.75
     Airways
    0.74
     renowned
    0.73
    icz
    0.73
    Act Density 0.053%

    No Known Activations