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

    Neuronpedia

    INDEX
    Explanations

    phrases with the word "if"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "if"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vez
    -0.73
    ngth
    -0.69
     contrace
    -0.64
     flux
    -0.63
     mosa
    -0.61
     CRA
    -0.59
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.58
    ADVERTISEMENT
    -0.57
     Vaugh
    -0.57
     Golem
    -0.56
    POSITIVE LOGITS
    ornia
    1.38
    ield
    1.04
    orce
    1.03
    amily
    0.98
    ftime
    0.92
    unction
    0.91
    rontal
    0.89
    cation
    0.88
    ieth
    0.87
    rag
    0.87
    Act Density 0.035%

    No Known Activations