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

    Neuronpedia

    INDEX
    Explanations

    words related to space travel or astronaut experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ì²
    -0.18
    олÑı
    -0.17
    -extra
    -0.15
    ivor
    -0.14
    Sharper
    -0.14
    _processing
    -0.14
    egrator
    -0.14
    osta
    -0.14
    yped
    -0.14
    atrice
    -0.14
    POSITIVE LOGITS
     preparation
    0.29
     prepar
    0.28
     preparations
    0.27
     prepare
    0.27
     prepares
    0.27
     preparing
    0.26
     prep
    0.26
    prepare
    0.25
     Preparation
    0.24
     pré
    0.24
    Act Density 0.012%

    No Known Activations