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

    Neuronpedia

    INDEX
    Explanations

    words related to legal and political entities

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ournals
    -0.87
    agues
    -0.70
    planet
    -0.68
     apart
    -0.67
    imedia
    -0.67
    ographers
    -0.65
    cloth
    -0.64
    女
    -0.64
     ingred
    -0.64
    genre
    -0.63
    POSITIVE LOGITS
     refusal
    1.38
     inability
    1.34
     efforts
    1.31
     attempts
    1.30
     insistence
    1.29
     decision
    1.29
     attempt
    1.28
     unwillingness
    1.23
     involvement
    1.21
     reluctance
    1.21
    Act Density 0.271%

    No Known Activations