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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "this."

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

    proper nouns starting with Thi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.62
     Kog
    -0.58
    Inflater
    -0.57
    hrens
    -0.56
    crats
    -0.55
     RER
    -0.55
    ruz
    -0.55
    ſelf
    -0.54
    featureID
    -0.53
    Opus
    -0.52
    POSITIVE LOGITS
     Thi
    2.27
    Thi
    2.19
     thi
    1.97
     THI
    1.38
    thi
    1.36
     Thiago
    1.18
     Thiel
    0.99
    thia
    0.96
    thie
    0.90
     Thiru
    0.85
    Act Density 0.005%

    No Known Activations