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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promoting ideas, activities, or causes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to promotion and advocacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Howe
    -0.73
     whence
    -0.70
     fry
    -0.66
     Bengal
    -0.65
     jaws
    -0.65
     pond
    -0.64
     wre
    -0.62
     disperse
    -0.61
    abouts
    -0.60
    ÄŁ
    -0.60
    POSITIVE LOGITS
    essim
    0.84
    Downloadha
    0.83
    amins
    0.83
    hovah
    0.79
    hemy
    0.76
    ocide
    0.75
     lifestyles
    0.74
    heit
    0.74
     ideals
    0.72
    clus
    0.71
    Act Density 0.268%

    No Known Activations