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

    Neuronpedia

    INDEX
    Explanations

    phrases related to instructions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the need to understand, learn, or view information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Sox
    -0.74
     benches
    -0.72
    luster
    -0.69
    ãĤ´ãĥ³
    -0.67
     pie
    -0.65
     lawy
    -0.64
    ItemTracker
    -0.64
    pie
    -0.63
     towels
    -0.60
     seams
    -0.59
    POSITIVE LOGITS
    ealous
    0.74
    ISE
    0.74
    hent
    0.73
     RELEASE
    0.71
     nutshell
    0.70
    uate
    0.69
     Kyl
    0.69
    ANCE
    0.63
    ovych
    0.62
     Lem
    0.60
    Act Density 0.164%

    No Known Activations