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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing uncertainty or potential outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lero
    -0.17
    ughs
    -0.16
    uhn
    -0.15
    jah
    -0.15
    dom
    -0.15
     Tiles
    -0.15
    ugs
    -0.14
    游
    -0.14
    adies
    -0.14
    inters
    -0.14
    POSITIVE LOGITS
     Stanton
    0.17
    igers
    0.17
    edar
    0.15
    ye
    0.15
    ikal
    0.15
    py
    0.15
     forest
    0.14
    ured
    0.14
    .CreateInstance
    0.14
    isque
    0.14
    Act Density 0.019%

    No Known Activations