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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ,:),
    -0.55
     Kombat
    -0.54
    MessageOf
    -0.54
     presentation
    -0.53
     presenting
    -0.52
    esModule
    -0.50
    didReceive
    -0.49
     Unsc
    -0.49
    EINVAL
    -0.49
    ⟬
    -0.48
    POSITIVE LOGITS
    NamedQueries
    0.64
     cherchés
    0.58
     виправивши
    0.58
     "..\..\..\
    0.58
    (!__
    0.55
     jambe
    0.55
     vícti
    0.55
    Rust
    0.54
    RUnlock
    0.54
    abestanden
    0.54
    Act Density 0.008%

    No Known Activations