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

    Neuronpedia

    INDEX
    Explanations

    the letter "E" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Eiffel Tower

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kenobi
    -0.76
     Anthem
    -0.70
     Showdown
    -0.65
    ãĤ¤ãĥĪ
    -0.65
    wagen
    -0.64
     pains
    -0.63
     Akira
    -0.62
     Nickel
    -0.61
     Bleach
    -0.61
    raints
    -0.60
    POSITIVE LOGITS
    nerg
    1.07
    fficient
    1.06
    ighty
    1.04
    isner
    1.04
    rect
    1.03
    ASY
    1.00
    lev
    1.00
    AST
    1.00
    resp
    1.00
    uter
    1.00
    Act Density 0.030%

    No Known Activations