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

    Neuronpedia

    INDEX
    Explanations

    repeated instances of the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    clauses starting with that or whether

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parallel
    -0.40
     intit
    -0.39
    databind
    -0.38
     inu
    -0.37
     address
    -0.37
    천
    -0.36
     email
    -0.36
     elabor
    -0.35
     fakt
    -0.35
     ram
    -0.34
    POSITIVE LOGITS
     utafitiHapana
    0.60
     CURIAM
    0.56
     Meksiku
    0.55
     okuyayım
    0.53
     tyle
    0.52
    setVerticalGroup
    0.52
    PostInfinity
    0.51
    Personendaten
    0.51
     Infórmanos
    0.51
    \{\\
    0.50
    Act Density 0.050%

    No Known Activations