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

    Neuronpedia

    INDEX
    Explanations

    various formatting symbols and structural elements in code or markup languages

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    וויק
    -0.71
     itſelf
    -0.68
     himo
    -0.63
    AnchorStyles
    -0.63
    --){
    -0.63
    idopsis
    -0.62
    CppCodeGen
    -0.62
    Begriffsklä
    -0.61
     bağlantılar
    -0.60
    InjectAttribute
    -0.59
    POSITIVE LOGITS
     siglas
    0.61
     virtuales
    0.57
     cuivre
    0.56
     franceses
    0.56
     sauvages
    0.56
    Disposed
    0.55
     nascita
    0.54
     femininas
    0.54
     afectadas
    0.53
     adelante
    0.53
    Act Density 0.365%

    No Known Activations