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

    Neuronpedia

    INDEX
    Explanations

    locations, addresses, and specific terms related to legal cases or historical events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    geographical locations and associated place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.04
    2:0.28
    3:0.11
    4:0.03
    5:0.05
    6:0.02
    7:0.02
    8:0.08
    9:0.15
    10:0.06
    11:0.03
    Negative Logits
     Gleaming
    -1.50
     Flavoring
    -1.44
     WWF
    -1.39
    issors
    -1.32
     Archdemon
    -1.29
     RSS
    -1.27
    MSN
    -1.23
     MAC
    -1.21
     autobiography
    -1.18
    装
    -1.17
    POSITIVE LOGITS
    ourses
    1.46
     bounds
    1.34
    onian
    1.33
     ante
    1.31
    ake
    1.23
    idences
    1.23
    Grade
    1.19
    pee
    1.19
    ials
    1.18
     aspir
    1.17
    Act Density 0.029%

    No Known Activations