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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "work" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anner
    -0.15
    gor
    -0.14
     Wave
    -0.14
    ily
    -0.14
    iyat
    -0.14
    igs
    -0.14
     Reaper
    -0.14
    jÃŃm
    -0.13
    undy
    -0.13
    olf
    -0.13
    POSITIVE LOGITS
    º
    0.17
    quina
    0.16
    shake
    0.15
    zeich
    0.15
    routeParams
    0.15
    rott
    0.15
     Papa
    0.15
    Ïģεί
    0.15
    дÑĸл
    0.14
     plu
    0.14
    Act Density 0.016%

    No Known Activations