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

    Neuronpedia

    INDEX
    Explanations

    names of locations or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly city names and notable entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     guiActiveUnfocused
    -0.78
     [&
    -0.78
     thereof
    -0.69
     thro
    -0.69
     Cth
    -0.63
     Cthulhu
    -0.62
     thereto
    -0.60
    isSpecialOrderable
    -0.59
     Teg
    -0.59
     Osiris
    -0.59
    POSITIVE LOGITS
    anyahu
    0.99
    elligence
    0.96
    asury
    0.95
    ropolitan
    0.94
    mond
    0.93
    odore
    0.93
    jamin
    0.92
    rique
    0.91
    ctions
    0.90
    alyst
    0.90
    Act Density 0.220%

    No Known Activations