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

    Neuronpedia

    INDEX
    Explanations

    words related to various international names or terms

    oai_token-act-pair · gpt-3.5-turbo

    the recurring mention of a character or entity throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    neys
    -0.83
    ienced
    -0.76
     Cosponsors
    -0.75
    library
    -0.75
    lasses
    -0.71
    manship
    -0.70
    RFC
    -0.70
    tails
    -0.67
    netic
    -0.67
    wolves
    -0.67
    POSITIVE LOGITS
    eus
    1.24
    uthor
    1.11
    isance
    0.90
    ples
    0.87
    ïve
    0.85
    veland
    0.84
    vel
    0.82
     Mae
    0.80
    wn
    0.78
    uth
    0.73
    Act Density 0.017%

    No Known Activations