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

    Neuronpedia

    INDEX
    Explanations

    indications of official or formal communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :
    -0.32
    ãģ¾ãģŁ
    -0.21
    ↵
    -0.21
    :↵
    -0.17
    :↵↵
    -0.17
     latter
    -0.17
    (
    -0.17
    antly
    -0.16
    à¹Į:
    -0.15
    COLUMN
    -0.15
    POSITIVE LOGITS
    innen
    0.21
    istrovstvÃŃ
    0.18
    odore
    0.16
    -↵
    0.15
    imas
    0.15
    /-
    0.15
    responseObject
    0.15
    ropolitan
    0.15
    oret
    0.15
    wealth
    0.14
    Act Density 0.518%

    No Known Activations