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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their experiences in a professional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inqu
    -0.17
    aln
    -0.16
     presidency
    -0.16
     Haven
    -0.15
    lete
    -0.15
    ÙĨدÙĬ
    -0.15
    ould
    -0.14
    ÙĨدÛĮ
    -0.14
    obe
    -0.14
     finishing
    -0.14
    POSITIVE LOGITS
     brings
    0.25
     bring
    0.23
     possess
    0.19
     held
    0.19
     rejo
    0.18
     poss
    0.18
     previously
    0.17
     most
    0.17
     possesses
    0.17
     comes
    0.16
    Act Density 0.057%

    No Known Activations