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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and their usage in relationships between phrases

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

    the conjunction "and" connecting clauses or ideas in complex sentences.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     there
    -0.42
     we
    -0.40
     they
    -0.38
     firstly
    -0.34
    /*
    -0.33
     and
    -0.30
     you
    -0.30
     both
    -0.29
    they
    -0.29
     kể
    -0.28
    POSITIVE LOGITS
     ſind
    0.79
    ThroughAttribute
    0.74
     <>",
    0.66
     Paglinawan
    0.66
    orsese
    0.63
    ſchaft
    0.63
    RegressionTest
    0.63
     thereby
    0.63
    从而
    0.61
     ſch
    0.60
    Act Density 0.634%

    No Known Activations