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

    Neuronpedia

    INDEX
    Explanations

    references to movement through a physical space

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and related phrases that indicate the presence of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    upload
    -0.67
    gov
    -0.67
    NAME
    -0.66
    POSE
    -0.65
    SHARE
    -0.64
    IAN
    -0.63
    Instance
    -0.63
    CTV
    -0.63
    Lead
    -0.62
    PO
    -0.62
    POSITIVE LOGITS
     motions
    1.20
     veins
    1.14
     haze
    1.11
     gates
    1.10
     ranks
    1.10
     entirety
    1.10
     maze
    1.08
     cracks
    1.07
     hoops
    1.06
     pores
    1.02
    Act Density 0.135%

    No Known Activations