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

    Neuronpedia

    INDEX
    Explanations

    mentions of specific types of food items, particularly those related to steaks

    oai_token-act-pair · gpt-3.5-turbo

    references to steak

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Leban
    -0.74
    ortium
    -0.73
    oral
    -0.73
    ucket
    -0.69
    IFIED
    -0.68
    eanor
    -0.66
    dash
    -0.66
     PowerPoint
    -0.64
    姫
    -0.62
    ei
    -0.62
    POSITIVE LOGITS
     ste
    0.91
    chnology
    0.87
    ampunk
    0.86
    ese
    0.85
    ste
    0.83
    achy
    0.81
    rers
    0.81
    uben
    0.80
    hett
    0.79
    amed
    0.78
    Act Density 0.007%

    No Known Activations