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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating restrictions or limitations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neau
    -0.20
    pok
    -0.16
    raud
    -0.14
    pom
    -0.14
    kinson
    -0.14
    ļ
    -0.14
    è´¹
    -0.14
    zia
    -0.14
    OSC
    -0.14
    itur
    -0.14
    POSITIVE LOGITS
     scope
    0.18
    idge
    0.17
    lessly
    0.17
     Liability
    0.17
     amount
    0.16
    odore
    0.16
    .Restr
    0.15
    ities
    0.15
     confines
    0.15
     scopes
    0.15
    Act Density 0.035%

    No Known Activations