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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people's names

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of specific patterns or fragments in names and terms related to individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    footed
    -0.64
     dracon
    -0.56
    nces
    -0.53
    Reviewer
    -0.53
     magnitude
    -0.52
    ctors
    -0.52
    unker
    -0.52
    pic
    -0.51
    urized
    -0.51
     thumb
    -0.50
    POSITIVE LOGITS
    opa
    0.81
    chal
    0.78
    uana
    0.73
    ela
    0.71
    quin
    0.67
    idate
    0.65
    adr
    0.64
     Wynne
    0.63
    atis
    0.62
    wine
    0.61
    Act Density 0.111%

    No Known Activations