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

    Neuronpedia

    INDEX
    Explanations

    numerical data and formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acre
    -0.17
    inch
    -0.16
    \Bridge
    -0.15
    inal
    -0.15
     Tob
    -0.14
    리카
    -0.14
    arendra
    -0.14
    agnost
    -0.14
    licit
    -0.14
     недел
    -0.14
    POSITIVE LOGITS
    fair
    0.15
    ìĸij
    0.15
     dikke
    0.14
    utos
    0.14
    kud
    0.14
     tiener
    0.14
    laz
    0.14
     gust
    0.14
     Coalition
    0.13
    rå
    0.13
    Act Density 0.016%

    No Known Activations