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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by specific locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that include the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ypes
    -0.88
    icia
    -0.81
    agy
    -0.81
    anan
    -0.78
    staking
    -0.76
    achus
    -0.73
    ornings
    -0.72
    tle
    -0.71
    itia
    -0.70
    shine
    -0.70
    POSITIVE LOGITS
     aforementioned
    0.93
    ses
    0.92
     latter
    0.88
     afore
    0.85
     latest
    0.81
     smallest
    0.81
     respective
    0.80
     shortest
    0.80
     slightest
    0.79
     remainder
    0.78
    Act Density 0.521%

    No Known Activations