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

    Neuronpedia

    INDEX
    Explanations

    the verb "disclose" and its variations

    oai_token-act-pair · gpt-4-turbo

    instances of the word "disclose" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "disclose" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vic
    -0.77
     Towns
    -0.65
    isol
    -0.65
     Cra
    -0.63
    oyal
    -0.63
     captcha
    -0.63
    Demand
    -0.63
    Fan
    -0.63
     stead
    -0.62
     crank
    -0.62
    POSITIVE LOGITS
     disclose
    1.06
     disclosing
    1.04
     discl
    1.01
     disclosures
    1.01
     disclosure
    0.96
     disclosed
    0.94
     Disclosure
    0.86
    metry
    0.79
    rets
    0.77
     confidential
    0.72
    Act Density 0.014%

    No Known Activations