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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating similarity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate comparisons or similarities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Score
    -0.62
    "},"
    -0.62
    ocene
    -0.60
    ————————
    -0.59
    aughs
    -0.56
    \/\/
    -0.55
    /"
    -0.55
    @@@@
    -0.55
    stay
    -0.54
    http
    -0.54
    POSITIVE LOGITS
     situated
    0.89
     minded
    0.79
    minded
    0.73
    ,
    0.67
     sized
    0.66
    apy
    0.66
     inclined
    0.65
    quartered
    0.65
    leep
    0.65
     importantly
    0.64
    Act Density 0.033%

    No Known Activations