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

    Neuronpedia

    INDEX
    Explanations

    terms related to financial and educational policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    206
    -0.15
     inadvertently
    -0.15
    ome
    -0.14
     foc
    -0.14
     genuine
    -0.14
     genuinely
    -0.14
    izzo
    -0.14
     unintention
    -0.14
     inadvert
    -0.14
     pleasantly
    -0.14
    POSITIVE LOGITS
     supposed
    0.16
    olec
    0.16
     subjective
    0.15
    aurant
    0.15
     justification
    0.14
     Orwell
    0.14
     convenient
    0.14
     instead
    0.14
    spin
    0.14
     spins
    0.14
    Act Density 0.814%

    No Known Activations