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

    Neuronpedia

    INDEX
    Explanations

    negative contractions and possessive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <eos>
    -0.50
    s
    -0.40
     rest
    -0.39
     predic
    -0.38
     or
    -0.38
     suff
    -0.38
     Sup
    -0.38
     Bal
    -0.38
     Po
    -0.38
    orElseThrow
    -0.37
    POSITIVE LOGITS
    rungsseite
    0.85
    tvguidetime
    0.78
    :✨
    0.73
     nonUne
    0.66
     Theſe
    0.66
     Monfieur
    0.64
     myſelf
    0.63
     plufieurs
    0.60
     Normdatei
    0.59
    Panamoan
    0.59
    Act Density 0.888%

    No Known Activations