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

    Neuronpedia

    INDEX
    Explanations

    the word "which" or related alternative pronouns used in clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     genoux
    -0.55
    bayern
    -0.54
     back
    -0.53
     bit
    -0.53
     sık
    -0.52
     potr
    -0.51
     Anz
    -0.51
    ileo
    -0.50
    兜
    -0.50
    ваний
    -0.50
    POSITIVE LOGITS
     auquel
    1.08
     springfox
    1.03
    ]")]
    0.94
     duquel
    0.93
    + 
    0.92
     WHICH
    0.92
     whereof
    0.88
    יצד
    0.85
    '],
    0.84
    Datuak
    0.84
    Act Density 0.102%

    No Known Activations