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

    Neuronpedia

    INDEX
    Explanations

    phrases that express continuity or persistence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.70
    Gön
    -0.70
    -0.68
    Gemeinden
    -0.64
    MigrationBuilder
    -0.63
    cular
    -0.61
     Lordships
    -0.61
    Geplaatst
    -0.60
    PyExc
    -0.60
     jScrollPane
    -0.60
    POSITIVE LOGITS
     always
    0.75
    昔から
    0.73
    Siempre
    0.70
     Always
    0.69
     Siempre
    0.68
    awsze
    0.68
    always
    0.67
     never
    0.66
    Always
    0.66
    我一直
    0.64
    Act Density 0.196%

    No Known Activations