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

    Neuronpedia

    INDEX
    Explanations

    points and distances in geometric contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     technique
    -0.07
     fine
    -0.07
     techniques
    -0.07
    okus
    -0.07
     literal
    -0.07
     okay
    -0.06
     to
    -0.06
    ites
    -0.06
     if
    -0.06
    ite
    -0.06
    POSITIVE LOGITS
    .intellij
    0.08
    jvu
    0.07
    à¤Łà¤¨
    0.07
     VÅ¡ech
    0.07
    *)((
    0.06
    åĭĴ
    0.06
     sóc
    0.06
    æ°ijæĹı
    0.06
    ÑĩеÑĢ
    0.06
    caf
    0.06
    Act Density 0.050%

    No Known Activations