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

    Neuronpedia

    INDEX
    Explanations

    phrases associated with decision-making and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reopening
    -0.18
     лÑĮ
    -0.15
    ếp
    -0.15
    keeper
    -0.14
    avi
    -0.14
    304
    -0.14
    жÑĥ
    -0.14
    ãģ®ãģĬ
    -0.14
    evi
    -0.14
     reopened
    -0.14
    POSITIVE LOGITS
     bail
    0.33
     quit
    0.33
     bolt
    0.29
     desert
    0.29
     pack
    0.28
     packed
    0.28
     walk
    0.27
     packing
    0.27
     packs
    0.26
     walked
    0.26
    Act Density 0.287%

    No Known Activations