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

    Neuronpedia

    INDEX
    Explanations

    specific scientific methodologies and experimental frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bre
    -0.16
     hele
    -0.15
     place
    -0.15
     derivation
    -0.15
    mere
    -0.14
    oli
    -0.14
    olist
    -0.14
     absolute
    -0.14
     peoples
    -0.13
    ago
    -0.13
    POSITIVE LOGITS
     novel
    0.20
     suite
    0.19
    toy
    0.18
    istrovstvÃŃ
    0.17
    anning
    0.17
     Novel
    0.16
    Toy
    0.16
    uran
    0.16
    ÑģÑıÑĤ
    0.16
     protocol
    0.16
    Act Density 0.199%

    No Known Activations