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

    Neuronpedia

    INDEX
    Explanations

    instances of the word 'disclose' or related forms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "disclose" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vic
    -0.88
    isol
    -0.77
    clock
    -0.69
    ieval
    -0.68
    JV
    -0.66
     stead
    -0.65
    twitch
    -0.65
    skill
    -0.65
    create
    -0.64
    creation
    -0.62
    POSITIVE LOGITS
     disclosures
    0.97
     loopholes
    0.96
     disclosure
    0.93
     disclosing
    0.92
     disclose
    0.92
     discl
    0.88
     Disclosure
    0.85
     disclosed
    0.85
     wrongdoing
    0.83
    parency
    0.76
    Act Density 0.020%

    No Known Activations