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

    Neuronpedia

    INDEX
    Explanations

    words related to the passage of time, events, and instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to emotional experiences and sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     controvers
    -0.56
     domestically
    -0.54
    oret
    -0.53
     subcontract
    -0.51
     triangles
    -0.50
     acquitted
    -0.49
     prototypes
    -0.48
     exceptions
    -0.48
     ambul
    -0.47
     theoretically
    -0.47
    POSITIVE LOGITS
    é¾įåĸļ士
    0.59
    EMBER
    0.58
    lege
    0.55
    âĹ¼
    0.53
    ORTS
    0.53
    ISSION
    0.53
    ISON
    0.51
    ĸļ
    0.51
    UNE
    0.51
     enthusi
    0.50
    Act Density 1.489%

    No Known Activations