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

    Neuronpedia

    INDEX
    Explanations

    terms related to using the internet for various activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" across different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    76561
    -0.81
    isin
    -0.70
    iac
    -0.67
    reciation
    -0.67
    fully
    -0.66
    manship
    -0.65
    TRY
    -0.64
    bourg
    -0.64
    lement
    -0.62
    accompanied
    -0.62
    POSITIVE LOGITS
     sly
    1.06
     streets
    1.03
     lookout
    1.01
     battlefield
    0.99
     brink
    0.99
     fly
    0.98
     verge
    0.98
     weekends
    0.98
     couch
    0.95
     prow
    0.92
    Act Density 0.126%

    No Known Activations