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

    Neuronpedia

    INDEX
    Explanations

    phrases emphasizing the presence of nouns and descriptors in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /Form
    -0.16
    άÏģ
    -0.15
     Slee
    -0.15
    oad
    -0.15
    ond
    -0.14
    گر
    -0.14
    OND
    -0.14
    ubber
    -0.14
    geb
    -0.14
    endum
    -0.14
    POSITIVE LOGITS
    linger
    0.18
    ishi
    0.17
    agrams
    0.16
    addresses
    0.15
    ausal
    0.15
    okol
    0.15
    stants
    0.14
    zos
    0.14
    uras
    0.14
    quisitions
    0.14
    Act Density 0.278%

    No Known Activations