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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software coding, instructions, and technical functionalities

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions used to introduce contrasting information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tnc
    -0.67
    Synopsis
    -0.63
    him
    -0.60
    hart
    -0.58
    bite
    -0.57
    hoe
    -0.57
     himself
    -0.56
    apolis
    -0.56
    animous
    -0.56
     Glas
    -0.54
    POSITIVE LOGITS
     beware
    1.26
    tons
    1.20
     fortunately
    1.01
     luckily
    0.99
    chery
    0.95
     excludes
    0.94
     unfortunately
    0.91
     unlike
    0.90
     interestingly
    0.87
     hey
    0.86
    Act Density 0.184%

    No Known Activations