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

    Neuronpedia

    INDEX
    Explanations

    specific mentions of locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" and context related to generational change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tickets
    -0.69
    ©¶æ
    -0.67
    arians
    -0.65
    nesty
    -0.65
    milo
    -0.65
    otte
    -0.64
    orsi
    -0.63
    rand
    -0.63
    raud
    -0.62
     accordingly
    -0.62
    POSITIVE LOGITS
     midst
    1.58
     depths
    1.40
     darkest
    1.27
     trenches
    1.22
     confines
    1.21
     realm
    1.21
     thro
    1.17
     twilight
    1.15
     wilderness
    1.13
     darkness
    1.13
    Act Density 0.255%

    No Known Activations