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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating time or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hjælp
    -0.60
     hjelp
    -0.58
     vær
    -0.57
     plads
    -0.52
    ęp
    -0.52
     vorbehalten
    -0.52
     dė
    -0.52
     desconoc
    -0.51
     this
    -0.51
     ķ
    -0.50
    POSITIVE LOGITS
    tically
    0.85
    mically
    0.80
    ially
    0.80
    aterally
    0.80
    ALLY
    0.79
    ally
    0.77
    logically
    0.77
    ificantly
    0.77
    atically
    0.77
    ologically
    0.76
    Act Density 0.620%

    No Known Activations