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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the significance or necessity of various actions or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ambre
    -0.18
    uter
    -0.16
    ure
    -0.15
    iggs
    -0.14
    itas
    -0.14
    λί
    -0.14
    kir
    -0.14
    ias
    -0.14
    zek
    -0.14
     dop
    -0.14
    POSITIVE LOGITS
    usercontent
    0.17
    ritz
    0.15
    ież
    0.14
    iye
    0.14
    _marshall
    0.14
    leston
    0.14
    .getAs
    0.14
    suspend
    0.13
    inja
    0.13
    onical
    0.13
    Act Density 0.141%

    No Known Activations