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

    Neuronpedia

    INDEX
    Explanations

    phrases related to events, activities, and actions taking place

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ses
    -0.32
    /or
    -0.26
    duct
    -0.19
    pired
    -0.18
    ducted
    -0.18
    ductive
    -0.17
    /her
    -0.16
    woke
    -0.16
    rew
    -0.15
    лÑĮ
    -0.15
    POSITIVE LOGITS
    orem
    0.47
    ories
    0.34
    oretical
    0.32
    notated
    0.31
    oret
    0.30
    ynchronously
    0.27
    olated
    0.25
    semble
    0.23
    aters
    0.23
    ward
    0.23
    Act Density 0.321%

    No Known Activations