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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "re" immediately followed by another word starting with 'p', primarily related to repurposing or reusing something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ur" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Unch
    -0.78
     Opportunity
    -0.71
     Pell
    -0.68
     Lawson
    -0.68
     Elliott
    -0.67
     Oblivion
    -0.66
     Dialogue
    -0.65
     Yel
    -0.64
     Crusader
    -0.63
     Lomb
    -0.62
    POSITIVE LOGITS
    pose
    1.28
    posed
    1.25
    posing
    1.23
    poses
    1.13
    rect
    1.04
    bing
    1.02
    atively
    1.02
    ricular
    0.97
    anium
    0.96
    facing
    0.96
    Act Density 0.036%

    No Known Activations