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

    Neuronpedia

    INDEX
    Explanations

    words related to reactions and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    -0.18
    ern
    -0.17
    kits
    -0.16
    ping
    -0.15
    enza
    -0.15
    passwd
    -0.15
    esen
    -0.14
    elters
    -0.14
    wik
    -0.14
    paid
    -0.14
    POSITIVE LOGITS
    ivate
    0.36
    ively
    0.26
    iveness
    0.25
    ives
    0.23
    aries
    0.21
    uator
    0.21
    rice
    0.19
    uate
    0.19
    ants
    0.19
    ual
    0.18
    Act Density 0.027%

    No Known Activations