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

    Neuronpedia

    INDEX
    Explanations

    brand names containing the substring "if"

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or phrases involving "if."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.71
    vez
    -0.64
     flux
    -0.64
     Vaugh
    -0.59
     Dominion
    -0.59
     resil
    -0.58
     mosa
    -0.57
     heating
    -0.56
     Golem
    -0.56
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.55
    POSITIVE LOGITS
    ornia
    1.42
    orce
    1.07
    ield
    1.06
    amily
    1.02
    ftime
    1.00
    rag
    0.98
    cation
    0.98
    unction
    0.97
    iably
    0.94
    riend
    0.92
    Act Density 0.020%

    No Known Activations