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

    Neuronpedia

    INDEX
    Explanations

    names of locations or establishments

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of places or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sina
    -0.66
     leftover
    -0.64
    é¾įå¥ij士
    -0.63
     altogether
    -0.63
     Nielsen
    -0.62
    #$#$
    -0.62
    ÙIJ
    -0.61
     Carnegie
    -0.61
     overtime
    -0.59
     Bethesda
    -0.59
    POSITIVE LOGITS
    uctions
    1.11
    ifles
    1.11
    eworks
    1.02
    ifts
    1.01
    istries
    0.98
    Ħ¢
    0.92
    iffs
    0.91
    astery
    0.90
    actor
    0.89
    onics
    0.88
    Act Density 0.251%

    No Known Activations