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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or protocols aimed at safety and prevention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    taking steps to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JpaRepository
    -0.53
     Chwiliwch
    -0.51
     Eureka
    -0.51
     Roskov
    -0.50
    niana
    -0.50
    heritance
    -0.50
     geſch
    -0.50
     getItemId
    -0.50
     FetchType
    -0.49
    enya
    -0.49
    POSITIVE LOGITS
     Maßnahmen
    0.68
     precautions
    0.59
     precau
    0.58
    regelen
    0.57
     measures
    0.50
     mesures
    0.49
     precaution
    0.48
    Precautions
    0.47
     Precautions
    0.47
     mesure
    0.46
    Act Density 0.024%

    No Known Activations