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

    Neuronpedia

    INDEX
    Explanations

    words related to people's names, especially those containing the letters "ram" or "on"

    oai_token-act-pair · gpt-3.5-turbo

    elements of the names of places or people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :{
    -0.65
    uyomi
    -0.63
     tentative
    -0.63
     perm
    -0.63
    DN
    -0.62
     horizont
    -0.60
     Assignment
    -0.59
    \<
    -0.59
    ymm
    -0.59
    vez
    -0.58
    POSITIVE LOGITS
    gow
    0.77
    xus
    0.72
    din
    0.68
    STD
    0.67
    rish
    0.66
    quin
    0.64
     Salam
    0.64
    isSpecialOrderable
    0.64
    rison
    0.63
    ufact
    0.63
    Act Density 0.195%

    No Known Activations