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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or significant arguments in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vocab
    -0.17
     spelling
    -0.17
    argon
    -0.16
    RTL
    -0.16
    è¨Ģèijī
    -0.16
    ýš
    -0.16
     vocabulary
    -0.15
     Gol
    -0.15
    .IContainer
    -0.15
     BASIS
    -0.15
    POSITIVE LOGITS
     interrog
    0.21
     imperson
    0.20
    atives
    0.20
     particles
    0.20
     modal
    0.20
     clause
    0.20
     Mood
    0.20
     particle
    0.19
    Particle
    0.18
     clauses
    0.17
    Act Density 0.016%

    No Known Activations