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

    Neuronpedia

    INDEX
    Explanations

    references to the letter "L" in various contexts, such as acronyms, words, or names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the letter 'L' or any variation including combinations with numbers and other characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Subtle
    -0.67
     prohibition
    -0.65
    hower
    -0.64
     compensated
    -0.62
    chell
    -0.62
     Satanic
    -0.62
     peg
    -0.60
     spirited
    -0.60
     actionGroup
    -0.59
    fulness
    -0.58
    POSITIVE LOGITS
    ifestyle
    1.36
    ighthouse
    1.32
    arger
    1.32
    yrics
    1.31
    aptop
    1.30
    ibrarian
    1.30
    ongevity
    1.28
    ateral
    1.28
    ONDON
    1.23
    ifest
    1.23
    Act Density 0.036%

    No Known Activations