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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and settings in a narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kontakte
    -0.15
     CascadeType
    -0.15
     perform
    -0.14
    wert
    -0.14
    Portrait
    -0.13
     sidelines
    -0.13
    amoto
    -0.13
     ãĤ±
    -0.13
    CSI
    -0.13
    ila
    -0.13
    POSITIVE LOGITS
     locations
    0.23
     location
    0.22
     Locations
    0.21
    -location
    0.21
     environments
    0.20
     scenes
    0.20
    Locations
    0.19
    locations
    0.19
     Settings
    0.19
    location
    0.18
    Act Density 0.388%

    No Known Activations