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

    Neuronpedia

    INDEX
    Explanations

    references to specific locations and details about places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    spatial location descriptions using prepositions and directional words.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.36
    autoreleasepool
    -0.34
    Portail
    -0.33
     recibo
    -0.31
    bkz
    -0.29
    +#+
    -0.29
     AssemblyTitle
    -0.29
    Portale
    -0.28
    PRNewswire
    -0.28
     kategor
    -0.28
    POSITIVE LOGITS
     upstairs
    1.46
     downstairs
    1.24
     floors
    1.09
     floor
    1.08
     étage
    1.01
     upper
    1.01
     basement
    1.00
    Upstairs
    1.00
    ชั้น
    0.95
     Floor
    0.94
    Act Density 0.108%

    No Known Activations