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

    Neuronpedia

    INDEX
    Explanations

    elements related to organizational or structural details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "
    -0.15
    ®
    -0.15
    sko
    -0.14
    âĶ¬
    -0.13
    ">-->↵
    -0.13
     "[
    -0.13
    orda
    -0.13
    ÂĹ
    -0.13
     sperma
    -0.13
    ç¨
    -0.13
    POSITIVE LOGITS
     favoured
    0.23
     programmes
    0.23
     behaviours
    0.21
     neighbours
    0.21
     honour
    0.21
     Honour
    0.20
     armour
    0.20
     Behaviour
    0.20
     honoured
    0.20
     neighbour
    0.19
    Act Density 0.002%

    No Known Activations