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

    Neuronpedia

    INDEX
    Explanations

    phrases prompting for opinions or thoughts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that prompt or inquire about opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vity
    -0.70
    acerb
    -0.69
    lite
    -0.68
    enegger
    -0.66
    wealth
    -0.64
    anmar
    -0.63
    abb
    -0.62
    gm
    -0.62
     nowhere
    -0.62
    inently
    -0.61
    POSITIVE LOGITS
     happened
    0.88
     about
    0.88
     happens
    0.87
     constitutes
    0.80
     deserves
    0.78
     awaits
    0.76
    fulness
    0.73
     inspires
    0.73
     ABOUT
    0.72
     belongs
    0.69
    Act Density 0.029%

    No Known Activations