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

    Neuronpedia

    INDEX
    Explanations

    names or instances of references within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to names or naming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    elaide
    -0.77
    yrinth
    -0.76
    istar
    -0.74
    psey
    -0.74
    romy
    -0.70
    isexual
    -0.68
    icult
    -0.67
    berra
    -0.67
     Smy
    -0.67
    iership
    -0.64
    POSITIVE LOGITS
    plates
    1.58
    plate
    1.48
    paces
    1.20
    paced
    1.01
    names
    0.95
    ames
    0.91
    calling
    0.91
     recognition
    0.90
    brand
    0.87
    akes
    0.84
    Act Density 0.046%

    No Known Activations