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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "if"

    oai_token-act-pair · gpt-3.5-turbo

    the conditional word "if" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.77
     Galile
    -0.64
     Learns
    -0.63
    emetery
    -0.62
    GGGG
    -0.62
    FTWARE
    -0.61
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.60
     contrace
    -0.60
    âĸ¬
    -0.60
    æĸ¹
    -0.58
    POSITIVE LOGITS
    ornia
    1.19
    acet
    0.95
    rontal
    0.94
    ield
    0.90
    rame
    0.89
    orce
    0.87
    uku
    0.86
    fy
    0.85
    unction
    0.84
    rit
    0.81
    Act Density 0.017%

    No Known Activations