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

    Neuronpedia

    INDEX
    Explanations

    the letter "e" as a standalone element

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'e' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Showdown
    -0.63
    ODY
    -0.60
     GEAR
    -0.60
     WARRANT
    -0.59
     Leaves
    -0.56
    ãĤ¤ãĥĪ
    -0.56
     Pick
    -0.56
    ourced
    -0.55
     helicopters
    -0.55
     Colleges
    -0.55
    POSITIVE LOGITS
    tymology
    1.40
    ternally
    1.21
    ller
    1.15
    fter
    1.13
    gypt
    1.12
    agles
    1.12
    thereal
    1.08
    got
    1.07
    lla
    1.00
    llo
    1.00
    Act Density 0.025%

    No Known Activations