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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to evaluations or judgments

    oai_token-act-pair · gpt-3.5-turbo

    words associated with various forms of challenges or conflicts in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blasio
    -0.56
     Wyr
    -0.55
     Helpful
    -0.55
     Rack
    -0.55
     Lank
    -0.54
    risome
    -0.50
    ridor
    -0.50
    ORN
    -0.50
     Kinnikuman
    -0.50
    INTON
    -0.50
    POSITIVE LOGITS
    ises
    0.73
    matically
    0.73
    fully
    0.70
    iets
    0.70
    ALLY
    0.70
    izes
    0.68
    heartedly
    0.68
     selves
    0.67
    iaries
    0.66
    lessly
    0.65
    Act Density 0.575%

    No Known Activations