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

    Neuronpedia

    INDEX
    Explanations

    words related to origins or historical beginnings

    oai_token-act-pair · gpt-3.5-turbo

    references to origins or foundational aspects of subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    roph
    -0.76
    tein
    -0.69
    affer
    -0.68
    onest
    -0.65
    eneg
    -0.65
    recomm
    -0.64
    jud
    -0.63
    obe
    -0.63
     Rabbit
    -0.62
    razil
    -0.62
    POSITIVE LOGITS
     Roots
    0.92
    hips
    0.86
    pring
    0.82
     roots
    0.81
    waters
    0.70
    ourcing
    0.69
    ystem
    0.68
     traced
    0.67
    sembly
    0.67
    ãĤ«
    0.66
    Act Density 0.033%

    No Known Activations