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

    Neuronpedia

    INDEX
    Explanations

    various section headers or formatting indicators within a structured document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atab
    -0.15
     another
    -0.14
    thur
    -0.13
    onen
    -0.13
    apr
    -0.13
    amber
    -0.13
    pei
    -0.13
    lds
    -0.13
    table
    -0.13
    otti
    -0.13
    POSITIVE LOGITS
     Purpose
    0.24
     purpose
    0.23
     PURPOSE
    0.22
    STRACT
    0.22
     aims
    0.22
     aim
    0.22
     Aim
    0.21
    BACKGROUND
    0.21
     Objective
    0.21
    缮çļĦ
    0.21
    Act Density 0.059%

    No Known Activations