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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating a significant change or difference

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant changes or increases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emis
    -0.83
    tein
    -0.79
    rity
    -0.77
    nan
    -0.77
    sburgh
    -0.76
    mates
    -0.71
    fman
    -0.70
    ourke
    -0.69
    imir
    -0.66
    amina
    -0.66
    POSITIVE LOGITS
     departure
    0.84
     change
    0.78
    ãĥ£
    0.77
     departures
    0.76
     amounts
    0.70
     divergence
    0.68
     curtail
    0.68
     alter
    0.67
     rethink
    0.67
    00007
    0.67
    Act Density 0.038%

    No Known Activations