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

    Neuronpedia

    INDEX
    Explanations

    verb phrases related to physical actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     fto
    -0.65
     dora
    -0.54
     jep
    -0.52
     sii
    -0.52
     fei
    -0.52
     fta
    -0.51
     demokra
    -0.51
     inder
    -0.51
     purcha
    -0.50
     nij
    -0.50
    POSITIVE LOGITS
     opponents
    0.77
     foes
    0.75
     enemies
    0.75
     opponent
    0.73
     enemy
    0.71
     getTarget
    0.64
     *++
    0.60
     Enemies
    0.59
     targets
    0.59
     adversaries
    0.59
    Act Density 0.520%

    No Known Activations