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

    Neuronpedia

    INDEX
    Explanations

    concepts related to real-world testing and evaluation of models in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥĩãĤ£ãĤ¢
    -0.15
    -guide
    -0.15
     Tang
    -0.15
    ãĥ¬ãĤ¹
    -0.15
    رات
    -0.15
    uide
    -0.14
     Trou
    -0.14
     shapes
    -0.14
     Mich
    -0.14
     punch
    -0.14
    POSITIVE LOGITS
    lette
    0.18
    LETTE
    0.15
    ulous
    0.15
    UIApplication
    0.15
    ffa
    0.15
     con
    0.14
    reno
    0.14
    ADOR
    0.14
     pii
    0.14
     case
    0.14
    Act Density 0.222%

    No Known Activations