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

    Neuronpedia

    INDEX
    Explanations

    concepts related to connections or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ï¸
    -0.16
    ilde
    -0.15
     relative
    -0.14
    olec
    -0.14
    EDI
    -0.13
    odi
    -0.13
    orda
    -0.13
    intern
    -0.13
    userinfo
    -0.13
    ynet
    -0.13
    POSITIVE LOGITS
     closely
    0.37
     somehow
    0.26
     directly
    0.24
     chặt
    0.23
     tightly
    0.22
     tighter
    0.22
     together
    0.21
     DIRECT
    0.21
     напÑĢÑıм
    0.20
     inex
    0.20
    Act Density 0.066%

    No Known Activations