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

    Neuronpedia

    INDEX
    Explanations

    phrases related to doubt and uncertainty

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

    a grip upon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bénévol
    -0.49
     Membre
    -0.43
     celos
    -0.43
    Cipher
    -0.43
     Palacios
    -0.43
    mochila
    -0.42
    affaires
    -0.41
    Membre
    -0.41
     createContext
    -0.41
     Zeller
    -0.40
    POSITIVE LOGITS
     مرئيه
    0.72
    RegistryLite
    0.69
    writeFieldEnd
    0.63
     AssemblyVersion
    0.57
    rinfo
    0.54
     Dord
    0.52
    Portail
    0.52
    andowski
    0.52
     relied
    0.51
     nakalista
    0.51
    Act Density 0.171%

    No Known Activations