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

    Neuronpedia

    INDEX
    Explanations

    the word "which" in various contexts

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

    "which" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    relative clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    -0.77
     toalha
    -0.69
    e
    -0.69
    an
    -0.65
     Cater
    -0.64
     Tief
    -0.63
    ținut
    -0.63
     Ryd
    -0.62
     Preguntas
    -0.62
     sık
    -0.61
    POSITIVE LOGITS
     "..\..\
    0.90
     tartalomajánló
    0.90
    yntaxException
    0.88
    LoS
    0.88
    GHIJKLM
    0.84
    Phosph
    0.83
    ');?>
    0.82
    \,.
    0.81
    ',['
    0.80
    TypedDataSet
    0.79
    Act Density 0.156%

    No Known Activations