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

    Neuronpedia

    INDEX
    Explanations

    titles and names of video games and electronic devices

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eele
    -0.84
    ariat
    -0.79
    ngth
    -0.76
    iman
    -0.69
    forth
    -0.69
    ussion
    -0.69
     detach
    -0.68
    inker
    -0.68
    hower
    -0.65
    wards
    -0.65
    POSITIVE LOGITS
    ãĥŁ
    0.82
    Cola
    0.67
    Death
    0.63
     Bloom
    0.61
    death
    0.61
    é¾įå
    0.60
    ãĤ±
    0.59
     unicorn
    0.58
    birth
    0.57
     Blossom
    0.57
    Act Density 0.118%

    No Known Activations