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

    Neuronpedia

    INDEX
    Explanations

    phrases related to achieving popularity and recognition

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of fame

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     halves
    -0.67
    cise
    -0.64
     Barg
    -0.62
     Grow
    -0.62
    atives
    -0.62
     Fir
    -0.61
    tein
    -0.60
    hematic
    -0.59
     tense
    -0.58
     Stab
    -0.58
    POSITIVE LOGITS
     fame
    0.97
    rities
    0.90
    frey
    0.88
    ously
    0.85
    æ©
    0.84
     tremend
    0.81
     Fame
    0.78
    uously
    0.76
    ilial
    0.76
    iqueness
    0.76
    Act Density 0.010%

    No Known Activations