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

    Neuronpedia

    INDEX
    Explanations

    adjectives and descriptive phrases related to character traits and qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    flater
    -0.19
    tees
    -0.19
    iggins
    -0.18
     Insecta
    -0.15
    poons
    -0.15
    Ñģен
    -0.15
    à¹Ģลย
    -0.15
    liga
    -0.14
     åĨĨ
    -0.14
    essor
    -0.14
    POSITIVE LOGITS
     pan
    0.16
    üm
    0.16
     mid
    0.16
    ron
    0.15
    ovenant
    0.15
     lines
    0.15
    lak
    0.15
    amac
    0.15
    aza
    0.14
    _fixture
    0.14
    Act Density 0.006%

    No Known Activations