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

    Neuronpedia

    INDEX
    Explanations

    phrases requesting feedback or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .simps
    -0.15
    comings
    -0.14
    isu
    -0.13
    onec
    -0.13
    .onViewCreated
    -0.13
    EPS
    -0.13
    .gs
    -0.13
    .cum
    -0.13
    hum
    -0.13
    upo
    -0.13
    POSITIVE LOGITS
     know
    0.24
     knows
    0.22
     savoir
    0.20
     ETA
    0.18
     Know
    0.17
    Know
    0.17
     saber
    0.16
     aware
    0.16
    know
    0.15
     biết
    0.14
    Act Density 0.019%

    No Known Activations