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

    Neuronpedia

    INDEX
    Explanations

    references to speakers and speaking engagements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ays
    -0.18
    ongs
    -0.17
    amas
    -0.17
    ildo
    -0.16
    /mit
    -0.16
    arily
    -0.15
    лÑıеÑĤ
    -0.15
    ated
    -0.15
    ters
    -0.15
    mes
    -0.14
    POSITIVE LOGITS
    stakes
    0.17
    phone
    0.16
     bure
    0.16
    iment
    0.15
    wdx
    0.15
    sterol
    0.15
    izoph
    0.15
    phones
    0.15
     bureau
    0.15
    ertest
    0.15
    Act Density 0.027%

    No Known Activations