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

    Neuronpedia

    INDEX
    Explanations

    words indicating necessity or obligation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ulent
    -0.18
     Ul
    -0.16
    olo
    -0.15
    zion
    -0.15
    istas
    -0.15
    ôi
    -0.15
    ULO
    -0.14
    ulle
    -0.14
     wet
    -0.14
    pcf
    -0.14
    POSITIVE LOGITS
    antly
    0.16
    лаÑģ
    0.15
     пÑĢеж
    0.15
    ë©´ìłģ
    0.15
    ensely
    0.15
    ocha
    0.15
    lesen
    0.15
     Daw
    0.14
    лÑıÑħ
    0.14
    Adv
    0.14
    Act Density 0.099%

    No Known Activations