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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and their influences in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     timeline
    -0.19
     impactful
    -0.18
     iconic
    -0.17
     backstory
    -0.17
     onboard
    -0.16
     headquartered
    -0.16
     pairwise
    -0.16
     WWII
    -0.16
     artwork
    -0.16
     standalone
    -0.15
    POSITIVE LOGITS
     foregoing
    0.22
     boasted
    0.21
     present
    0.21
     meshes
    0.20
     pretended
    0.20
     especial
    0.20
     whole
    0.19
     utmost
    0.19
     chief
    0.18
     connexion
    0.18
    Act Density 0.260%

    No Known Activations