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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize continuity and persistence over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     bezeichneter
    -0.64
     précédente
    -0.61
     estekak
    -0.60
    клопе
    -0.59
     lenker
    -0.57
     Houſe
    -0.57
    erequisites
    -0.57
     חיצוניים
    -0.57
    первых
    -0.55
     Previous
    -0.54
    POSITIVE LOGITS
     tutt
    0.78
     still
    0.72
    still
    0.68
    至今
    0.65
    今でも
    0.64
    今も
    0.63
     fortfarande
    0.61
    ัจ
    0.59
     geblieben
    0.56
     fortsatt
    0.55
    Act Density 0.224%

    No Known Activations