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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals or groups with specific traits or conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    henko
    -0.72
    cade
    -0.65
    Fed
    -0.62
    rail
    -0.62
    ouf
    -0.60
    FIG
    -0.59
     afterward
    -0.59
    press
    -0.57
    oult
    -0.56
     afterwards
    -0.56
    POSITIVE LOGITS
    stood
    1.50
     disabilities
    1.45
     whom
    1.19
    drawn
    1.15
    standing
    1.11
     regard
    1.06
     regards
    0.99
    held
    0.97
     respect
    0.95
     aspirations
    0.94
    Act Density 0.110%

    No Known Activations