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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "which" or its variants in complex sentence structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ₂+
    -0.55
     Berufs
    -0.50
    yyb
    -0.47
    reathable
    -0.47
     slides
    -0.45
     Monfieur
    -0.45
     Stats
    -0.44
     feroit
    -0.44
     مشين
    -0.43
    ktı
    -0.43
    POSITIVE LOGITS
    Whom
    0.66
     whom
    0.61
    where
    0.61
    whom
    0.60
    Where
    0.58
    wherein
    0.58
     wherein
    0.56
    which
    0.56
    Which
    0.54
     waarin
    0.54
    Act Density 0.139%

    No Known Activations