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

    Neuronpedia

    INDEX
    Explanations

    sentences starting with "This" or "These" that introduce specific ideas or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogan
    -0.18
     certain
    -0.15
     bail
    -0.15
     i
    -0.15
     Crab
    -0.15
    sm
    -0.14
    io
    -0.14
    enus
    -0.14
     Fore
    -0.14
     baj
    -0.14
    POSITIVE LOGITS
    istro
    0.15
    ityEngine
    0.15
    geber
    0.15
    èĢ
    0.15
    εÏģι
    0.15
    teri
    0.15
    deÅŁ
    0.15
    PTH
    0.14
    uner
    0.14
    pto
    0.14
    Act Density 0.069%

    No Known Activations