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

    Neuronpedia

    INDEX
    Explanations

    mentions of rumors and news updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    kin
    -0.15
     grap
    -0.15
    cin
    -0.14
     task
    -0.14
    .ut
    -0.14
    hower
    -0.13
    egen
    -0.13
    nist
    -0.13
     permanently
    -0.13
     duty
    -0.13
    POSITIVE LOGITS
     sources
    0.19
    ixe
    0.17
     Sources
    0.16
    Leaks
    0.16
     Exclusive
    0.15
    Exclusive
    0.15
    sources
    0.15
     à¹Ģà¸ĩ
    0.15
     source
    0.15
     exclusive
    0.15
    Act Density 0.041%

    No Known Activations