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

    Neuronpedia

    INDEX
    Explanations

    references to immigration tiers and visa categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agers
    -0.15
    zion
    -0.14
    ycz
    -0.14
    rud
    -0.13
    nic
    -0.13
    ullen
    -0.13
    serie
    -0.13
    bject
    -0.13
    vae
    -0.13
     дело
    -0.13
    POSITIVE LOGITS
    edImage
    0.24
    ed
    0.21
    edList
    0.21
    次
    0.20
    ney
    0.18
    AccessException
    0.16
    ing
    0.16
    -scalable
    0.15
    neys
    0.15
    NEY
    0.15
    Act Density 0.010%

    No Known Activations