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

    Neuronpedia

    INDEX
    Explanations

    words related to insurance and reassurance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to insurance or assurance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pav
    -0.67
     mug
    -0.66
     resh
    -0.65
    via
    -0.63
     dissect
    -0.62
     det
    -0.62
    git
    -0.62
     stir
    -0.61
    KEY
    -0.61
     tap
    -0.61
    POSITIVE LOGITS
    urance
    4.82
    urances
    2.79
    urers
    2.01
    urer
    1.63
    pection
    1.39
    uring
    1.32
    ured
    1.30
    essment
    1.25
    ures
    1.18
    tenance
    1.17
    Act Density 0.015%

    No Known Activations