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

    Neuronpedia

    INDEX
    Explanations

    prompts asking for opinions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    inquiries or prompts asking for the reader's opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    clad
    -0.75
    devices
    -0.71
     Adin
    -0.69
    wealth
    -0.64
    arer
    -0.61
    announced
    -0.61
    iencies
    -0.61
    begin
    -0.59
    Kn
    -0.59
    miss
    -0.59
    POSITIVE LOGITS
     constitu
    0.76
    rison
    0.71
    estyles
    0.69
     ABOUT
    0.68
    orean
    0.67
    imaru
    0.67
    ortal
    0.66
    ashington
    0.65
    elson
    0.65
     about
    0.65
    Act Density 0.044%

    No Known Activations