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

    Neuronpedia

    INDEX
    Explanations

    mentions of family members or relatives, especially uncles

    oai_token-act-pair · gpt-3.5-turbo

    references to various family members, particularly uncles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mberg
    -0.92
    ãĤ¤ãĥĪ
    -0.75
    isers
    -0.71
    EVA
    -0.67
    istas
    -0.66
     revolving
    -0.64
    veyard
    -0.63
     cancellation
    -0.62
     largeDownload
    -0.62
    ization
    -0.61
    POSITIVE LOGITS
     uncle
    1.10
    ired
    0.91
    liest
    0.90
    aned
    0.89
    hest
    0.88
     nephew
    0.84
     niece
    0.80
    rieved
    0.80
    hetically
    0.79
     Uncle
    0.78
    Act Density 0.012%

    No Known Activations