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

    Neuronpedia

    INDEX
    Explanations

    phrases related to size, scale, and severity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uba
    -0.80
    ãĤ´ãĥ³
    -0.79
    icia
    -0.74
    agy
    -0.74
    iably
    -0.73
    adata
    -0.72
    olulu
    -0.70
    nesty
    -0.70
    wash
    -0.70
    amar
    -0.70
    POSITIVE LOGITS
     respective
    1.07
     entire
    1.04
     aforementioned
    0.99
     latter
    0.93
     smallest
    0.92
     individual
    0.84
     greatest
    0.84
     relationship
    0.82
     sexes
    0.82
     weakest
    0.82
    Act Density 0.254%

    No Known Activations