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

    Neuronpedia

    INDEX
    Explanations

    names starting with "Merv"

    oai_token-act-pair · gpt-3.5-turbo

    references to a person's name, particularly in relation to their actions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fine
    -0.64
    ©¶æ
    -0.61
     stumbling
    -0.58
     outdoors
    -0.57
     LCS
    -0.57
    lihood
    -0.56
     quantities
    -0.56
     contrad
    -0.54
     distinguishing
    -0.54
     excluding
    -0.54
    POSITIVE LOGITS
    asive
    1.27
    atism
    1.27
    oir
    1.12
    iced
    1.09
    oice
    1.03
    iew
    0.98
    icing
    0.97
    icious
    0.92
    ices
    0.91
    ance
    0.89
    Act Density 0.042%

    No Known Activations