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

    Neuronpedia

    INDEX
    Explanations

    the pronoun "it" and its various usages in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.68
    Republic
    -0.68
    anton
    -0.66
    ullivan
    -0.66
    hips
    -0.65
    untled
    -0.63
    priv
    -0.62
    arthed
    -0.62
    noticed
    -0.62
     Corpus
    -0.61
    POSITIVE LOGITS
     ain
    1.25
     happens
    1.12
     happened
    1.09
     hurts
    1.09
     involves
    1.07
     lasts
    1.01
    chy
    1.01
     sucks
    1.00
     exists
    1.00
     seems
    0.99
    Act Density 0.157%

    No Known Activations