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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "were" referring to actions or processes in experimental procedures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tanleria
    -0.68
    Hentet
    -0.66
    معلومات
    -0.57
    PointerException
    -0.56
    Cyfeiriadau
    -0.55
    ViewImports
    -0.54
    "}";
    -0.54
    */)
    -0.54
     AssemblyCompany
    -0.53
     météo
    -0.52
    POSITIVE LOGITS
    Bite
    0.56
     mening
    0.53
     intptr
    0.52
     quiver
    0.51
    capac
    0.50
     gauss
    0.50
    Precise
    0.50
     cannibal
    0.49
    SEGUIR
    0.49
    WebVitals
    0.49
    Act Density 0.027%

    No Known Activations