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

    Neuronpedia

    INDEX
    Explanations

    instances of identifiers and IDs within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĻĤ
    -1.81
    gro
    -1.59
    quart
    -1.59
     ÃĤ
    -1.57
    ↵  âĢĥ
    -1.57
      ↵
    -1.57
    ↵
    -1.57
    -1.57
    ↵↵↵
    -1.57
    ↵↵
    -1.57
    POSITIVE LOGITS
     necrosis
    1.50
     stripes
    1.50
    ycin
    1.43
    udeau
    1.40
    ctica
    1.38
    ivated
    1.35
    datetime
    1.33
    ubot
    1.33
     Providence
    1.31
    ives
    1.27
    Act Density 0.227%

    No Known Activations