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

    Neuronpedia

    INDEX
    Explanations

    assertions or claims about trustworthiness in various contexts

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

    guarantees, dangers, or reductions

    np_acts-logits-general · gemini-2.0-flash

    assurance and risk management

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     noqa
    -0.55
     concorso
    -0.51
     ihop
    -0.51
     BeautifulSoup
    -0.50
    niosek
    -0.49
    ientôt
    -0.47
     försö
    -0.46
     retali
    -0.46
     gepubliceerd
    -0.45
     تلاش
    -0.44
    POSITIVE LOGITS
     assurance
    1.23
     assurances
    1.19
     reassurance
    1.17
     risk
    1.15
     safety
    1.14
     trust
    1.10
     security
    1.06
     Risk
    1.05
     risks
    1.04
     reassuring
    1.03
    Act Density 0.377%

    No Known Activations