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

    Neuronpedia

    INDEX
    Explanations

    references to updates or new information in various contexts or scenarios

    oai_token-act-pair · gpt-3.5-turbo

    terms related to updates and modifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.74
    NetMessage
    -0.73
    zees
    -0.71
    ulhu
    -0.68
    WOOD
    -0.68
    PLIED
    -0.67
    baum
    -0.67
    ilyn
    -0.65
    dding
    -0.64
    hov
    -0.63
    POSITIVE LOGITS
     wording
    0.79
     rosters
    0.76
     menus
    0.75
     existing
    0.74
     constitution
    0.73
     reservation
    0.73
     fronts
    0.71
     timeline
    0.71
     menu
    0.71
     layout
    0.70
    Act Density 0.264%

    No Known Activations