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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating favorable choices or recommendations for accommodations and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olist
    -0.16
    antee
    -0.16
    inge
    -0.16
    incip
    -0.15
    ãĥ³ãĥĶ
    -0.15
    foy
    -0.14
    宿
    -0.14
    orer
    -0.14
    dea
    -0.14
     Bet
    -0.14
    POSITIVE LOGITS
     option
    0.17
    332
    0.16
     for
    0.16
    خش
    0.15
    iras
    0.14
    .struts
    0.14
     alternative
    0.14
    fiber
    0.14
    amar
    0.14
     âĹĦ
    0.14
    Act Density 0.151%

    No Known Activations