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

    Neuronpedia

    INDEX
    Explanations

    words related to issues, legal terms, and specific names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences and variations of the word "miss" or related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     balloons
    -0.61
     augmented
    -0.58
     dynamically
    -0.57
     Games
    -0.57
     cages
    -0.57
     dwar
    -0.57
     shortened
    -0.57
     metaphors
    -0.56
    WAYS
    -0.56
     Kash
    -0.56
    POSITIVE LOGITS
    iss
    4.49
    ISS
    2.41
    isse
    2.14
    issy
    1.62
    isson
    1.49
    issa
    1.36
    itzerland
    1.32
    ission
    1.31
    ouri
    1.27
    is
    1.26
    Act Density 0.018%

    No Known Activations