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

    Neuronpedia

    INDEX
    Explanations

    the string "ME" in all caps

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or organization, indicated by its frequent mention of "ME"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inyl
    -0.78
    raviolet
    -0.77
    lines
    -0.73
    inates
    -0.71
    iosity
    -0.69
    ulation
    -0.68
    lined
    -0.67
    tyard
    -0.66
    kefeller
    -0.66
    inating
    -0.65
    POSITIVE LOGITS
    ISTER
    0.95
    ME
    0.95
    ETS
    0.93
    LL
    0.92
    PS
    0.89
    ET
    0.86
    conom
    0.86
    FU
    0.85
    AKING
    0.81
    ENSE
    0.81
    Act Density 0.003%

    No Known Activations