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

    Neuronpedia

    INDEX
    Explanations

    common conjunctions and phrases indicating conditional or contrasting relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    적으로
    -0.51
     vian
    -0.44
    ulent
    -0.42
    jší
    -0.42
    ようになった
    -0.41
    nya
    -0.38
    ToAction
    -0.38
    elit
    -0.35
    IVATE
    -0.35
    적인
    -0.35
    POSITIVE LOGITS
     ostavi
    1.20
    UnsafeEnabled
    1.10
    verwijspagina
    1.09
     nakalista
    1.07
     &___
    1.07
     Vikipedi
    1.04
    tvguidetime
    1.02
    InjectAttribute
    1.02
     gynnwys
    0.97
    лтемелер
    0.96
    Act Density 0.884%

    No Known Activations