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

    Neuronpedia

    INDEX
    Explanations

    words related to interactions or relationships between different entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "inter" in various contexts, indicating a focus on interconnectedness or interplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.75
    ongs
    -0.67
    BuyableInstoreAndOnline
    -0.67
    \\\\\\\\
    -0.67
    hyde
    -0.66
    士
    -0.64
    FUL
    -0.64
    aughs
    -0.63
    OCK
    -0.62
    ij士
    -0.62
    POSITIVE LOGITS
    lude
    1.05
    racial
    1.01
    continental
    1.01
    dimensional
    0.98
    locking
    0.97
    cession
    0.96
    mitt
    0.96
    stitial
    0.95
    disciplinary
    0.93
    ventions
    0.93
    Act Density 0.013%

    No Known Activations