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

    Neuronpedia

    INDEX
    Explanations

    questions and expressions of inquiry

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    reck
    -0.15
    ré
    -0.14
    ills
    -0.14
    scar
    -0.14
    üre
    -0.14
    quil
    -0.14
    lore
    -0.14
    меÑĩ
    -0.14
    rai
    -0.14
    rig
    -0.14
    POSITIVE LOGITS
    zzo
    0.26
    ospace
    0.26
    nda
    0.24
    ady
    0.23
    nds
    0.23
    tha
    0.19
    nd
    0.19
    tap
    0.18
    nts
    0.18
    psilon
    0.18
    Act Density 0.065%

    No Known Activations