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

    Neuronpedia

    INDEX
    Explanations

    legal terminology and references to lawsuits

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the preposition "in."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¤ãĥĪ
    -0.79
     subscrib
    -0.76
    bsite
    -0.75
    CLASSIFIED
    -0.74
    ¶æ
    -0.62
    KNOWN
    -0.62
     knows
    -0.61
     mastered
    -0.60
     outputs
    -0.60
     clocks
    -0.59
    POSITIVE LOGITS
     favor
    1.33
     court
    1.17
    jury
    1.08
     favour
    1.07
     lieu
    0.99
     vitro
    0.97
    humane
    0.95
     behalf
    0.94
     conjunction
    0.93
     Court
    0.92
    Act Density 0.120%

    No Known Activations