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

    Neuronpedia

    INDEX
    Explanations

    mentions of software development and technical details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    715
    -0.16
    -transitional
    -0.15
    bens
    -0.14
    idot
    -0.14
    abox
    -0.14
    yonel
    -0.14
    uger
    -0.14
    enment
    -0.14
    haul
    -0.14
    PILE
    -0.14
    POSITIVE LOGITS
     dann
    0.24
     grave
    0.22
     grav
    0.21
     mortal
    0.19
     fer
    0.19
     ister
    0.18
     ro
    0.18
     fur
    0.18
     mort
    0.18
     violent
    0.18
    Act Density 0.003%

    No Known Activations