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

    Neuronpedia

    INDEX
    Explanations

    prepositional phrases that indicate a specific point in time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating prior actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    among
    -0.99
     largeDownload
    -0.74
    atic
    -0.70
    Rated
    -0.70
    Girls
    -0.68
    LED
    -0.67
    backed
    -0.66
    along
    -0.66
    tw
    -0.65
    <?
    -0.65
    POSITIVE LOGITS
     embark
    1.02
     completion
    0.88
     signing
    0.82
    imester
    0.81
     takeoff
    0.81
     sunset
    0.81
     arrival
    0.80
     expiration
    0.79
     commencement
    0.79
     sunrise
    0.78
    Act Density 0.047%

    No Known Activations