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

    Neuronpedia

    INDEX
    Explanations

    references to quality or superiority in comparison to others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    away
    -0.17
    ych
    -0.16
    ned
    -0.15
    nel
    -0.15
    ernaut
    -0.15
    TO
    -0.14
    erson
    -0.14
    ep
    -0.14
    åĦ¿
    -0.14
    urning
    -0.14
    POSITIVE LOGITS
    -quality
    0.25
    iors
    0.21
    ior
    0.21
    iets
    0.19
     quality
    0.17
    quality
    0.17
     вÑģего
    0.17
    owl
    0.17
    -most
    0.16
    haps
    0.16
    Act Density 0.010%

    No Known Activations