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

    Neuronpedia

    INDEX
    Explanations

    frequency of conjunctions and punctuation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     everything
    -0.69
     a
    -0.66
    <eos>
    -0.64
     work
    -0.63
     all
    -0.63
     this
    -0.62
    -
    -0.61
     network
    -0.58
     services
    -0.57
     system
    -0.57
    POSITIVE LOGITS
    URLException
    1.20
     ainfi
    1.20
     feroit
    1.12
     avoient
    1.10
     Monfieur
    1.06
     auroit
    1.06
     Efq
    1.04
     suivants
    0.98
    bbene
    0.98
     étoient
    0.96
    Act Density 0.734%

    No Known Activations