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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that include the prefix "pre-"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antan
    -0.18
    so
    -0.16
    sterdam
    -0.15
    arella
    -0.15
    v
    -0.15
    PropertyChanged
    -0.15
    /he
    -0.15
    sole
    -0.14
    ride
    -0.14
    la
    -0.14
    POSITIVE LOGITS
    ursors
    0.16
    PFN
    0.16
    /post
    0.15
    /original
    0.15
    umat
    0.15
    urette
    0.15
    (before
    0.14
     stage
    0.14
    mise
    0.14
    Ģ
    0.14
    Act Density 0.051%

    No Known Activations