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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reputation, especially negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "reputation"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cise
    -0.87
    pheus
    -0.77
    wed
    -0.75
    tein
    -0.72
    nes
    -0.72
    stad
    -0.70
    vention
    -0.68
    phone
    -0.67
    err
    -0.64
    apor
    -0.64
    POSITIVE LOGITS
     tarn
    0.96
     reputation
    0.95
     bearer
    0.81
    worthiness
    0.77
     tremend
    0.77
     forged
    0.75
    ously
    0.73
     internationally
    0.73
     abroad
    0.72
    arily
    0.71
    Act Density 0.080%

    No Known Activations