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

    Neuronpedia

    INDEX
    Explanations

    references to related work and methodologies in an academic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ESIS
    -0.15
    oda
    -0.15
    ITEM
    -0.15
    ίÏĥ
    -0.14
    asin
    -0.14
    inish
    -0.14
    iran
    -0.14
    ARAM
    -0.14
    ero
    -0.14
    лаб
    -0.14
    POSITIVE LOGITS
     feder
    0.15
    numer
    0.15
     bastard
    0.14
     Skip
    0.14
     numer
    0.14
    Skip
    0.14
    Ĥæķ°
    0.13
    ites
    0.13
     Suites
    0.13
    ILD
    0.13
    Act Density 0.066%

    No Known Activations