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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical movement or change in position

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to movement or actions involving positioning or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Brach
    -0.70
    Truth
    -0.65
    ottest
    -0.64
     è£ıè
    -0.64
    Crash
    -0.62
    PLIED
    -0.62
    Hour
    -0.62
    Uncommon
    -0.62
     Reconstruction
    -0.61
    MAL
    -0.61
    POSITIVE LOGITS
     closer
    0.87
     forwards
    0.86
    izont
    0.85
     forward
    0.84
     furthe
    0.80
     cursor
    0.78
     clocks
    0.77
     farther
    0.77
     onto
    0.76
     indoors
    0.76
    Act Density 0.166%

    No Known Activations