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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "inform" and related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inders
    -0.16
    gear
    -0.15
    oras
    -0.15
    uliar
    -0.15
    chers
    -0.14
    ucky
    -0.14
    ovnÃŃ
    -0.14
    grade
    -0.14
    sta
    -0.14
    з
    -0.13
    POSITIVE LOGITS
    ally
    0.27
    atics
    0.23
    ative
    0.22
    acje
    0.19
    idable
    0.18
    ants
    0.17
    ercial
    0.17
     about
    0.17
     ìĤ¬íķŃ
    0.16
    atica
    0.16
    Act Density 0.022%

    No Known Activations