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

    Neuronpedia

    INDEX
    Explanations

    references to a specific individual or entity, often identified by the initial "L" or similar tokens

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Negative Logits
     ls
    -0.77
     l
    -0.70
     ll
    -0.69
     lt
    -0.59
     lc
    -0.59
     lli
    -0.57
     langer
    -0.56
     lari
    -0.55
     lm
    -0.54
     lle
    -0.53
    POSITIVE LOGITS
    l
    0.74
    netinet
    0.71
    windowFixed
    0.71
     XCTest
    0.71
    //
    0.68
    Zeneca
    0.68
    ISupport
    0.64
    SizeF
    0.63
    demia
    0.62
    Kjelder
    0.62
    Act Density 0.022%

    No Known Activations