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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uger
    -0.18
    CLUD
    -0.15
    azen
    -0.15
    rez
    -0.15
    noc
    -0.14
    ieur
    -0.14
    ализи
    -0.14
    ContentType
    -0.14
    æħĭ
    -0.14
    orest
    -0.14
    POSITIVE LOGITS
     beyond
    0.35
     reach
    0.32
     reaching
    0.31
     Beyond
    0.31
     reaches
    0.31
    eyond
    0.30
     reached
    0.27
    Beyond
    0.26
     far
    0.26
     Reach
    0.25
    Act Density 0.172%

    No Known Activations