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

    Neuronpedia

    INDEX
    Explanations

    words related to attractiveness or desirability

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to attractiveness or interest to people, particularly in the context of products, ideas, or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ñĥ
    -0.78
     Colleges
    -0.74
    ifa
    -0.72
     Rost
    -0.67
    metal
    -0.66
     Berk
    -0.66
    kson
    -0.65
     Brut
    -0.63
     Coh
    -0.62
    fters
    -0.62
    POSITIVE LOGITS
     Flavoring
    1.12
    ingly
    0.97
    yrinth
    0.94
    ocene
    0.92
    ously
    0.88
    minist
    0.84
    atism
    0.84
    ĸļ
    0.81
    ikawa
    0.74
    eals
    0.74
    Act Density 0.017%

    No Known Activations